diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json" new file mode 100644--- /dev/null +++ "b/model.safetensors.index.json" @@ -0,0 +1 @@ +{"metadata": {"total_size": "211581925472"}, "weight_map": {"model.layers.0.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.11.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.12.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.13.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.14.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.15.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.16.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.17.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.18.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.19.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.2.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.20.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.21.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.22.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.23.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.24.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.25.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.26.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.27.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.28.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.29.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.3.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.30.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.31.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.32.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.33.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.34.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.35.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.36.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.37.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.38.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.39.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.4.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.40.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.41.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.42.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.43.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.44.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.45.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.46.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.47.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.48.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.49.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.5.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.50.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.51.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.52.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.53.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.54.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.55.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.56.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.57.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.58.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.59.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.6.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.60.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.61.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.7.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.8.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "model.layers.9.block_sparse_moe.e_score_correction_bias": "model-00001-of-00020.safetensors", "lm_head.weight": "model-00001-of-00020.safetensors", "model.embed_tokens.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.100.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.100.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.100.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.101.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.101.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.101.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.102.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.102.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.102.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.103.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.103.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.103.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.104.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.104.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.104.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.105.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.105.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.105.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.106.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.106.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.106.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.107.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.107.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.107.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.108.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.108.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.108.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.109.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.109.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.109.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.110.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.110.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.110.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.111.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.111.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.111.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.112.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.112.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.112.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.113.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.113.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.113.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.114.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.114.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.114.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.115.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.115.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.115.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.64.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.64.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.64.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.65.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.65.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.65.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.66.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.66.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.66.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.67.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.67.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.67.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.68.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.68.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.68.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.69.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.69.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.69.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.70.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.70.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.70.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.71.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.71.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.71.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.72.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.72.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.72.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.73.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.73.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.73.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.74.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.74.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.74.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.75.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.75.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.75.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.76.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.76.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.76.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.77.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.77.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.77.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.78.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.78.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.78.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.79.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.79.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.79.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.80.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.80.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.80.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.81.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.81.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.81.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.82.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.82.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.82.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.83.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.83.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.83.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.84.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.84.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.84.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.85.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.85.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.85.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.86.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.86.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.86.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.87.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.87.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.87.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.88.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.88.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.88.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.89.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.89.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.89.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.90.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.90.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.90.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.91.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.91.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.91.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.92.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.92.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.92.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.93.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.93.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.93.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.94.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.94.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.94.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.95.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.95.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.95.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.96.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.96.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.96.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.97.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.97.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.97.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.98.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.98.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.98.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.99.w1.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.99.w2.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.99.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00020.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.100.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.100.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.100.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.101.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.101.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.101.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.102.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.102.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.102.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.103.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.103.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.103.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.104.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.104.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.104.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.105.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.105.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.105.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.106.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.106.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.106.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.107.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.107.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.107.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.108.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.108.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.108.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.109.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.109.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.109.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.110.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.110.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.110.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.111.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.111.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.111.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.112.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.112.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.112.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.113.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.113.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.113.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.114.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.114.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.114.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.115.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.115.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.115.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.43.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.43.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.43.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.44.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.44.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.44.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.45.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.45.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.45.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.46.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.46.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.46.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.47.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.47.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.47.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.48.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.48.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.48.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.49.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.49.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.49.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.50.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.50.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.50.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.51.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.51.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.51.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.52.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.52.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.52.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.53.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.53.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.53.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.54.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.54.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.54.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.55.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.55.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.55.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.56.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.56.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.56.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.57.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.57.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.57.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.58.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.58.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.58.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.59.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.59.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.59.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.60.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.60.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.60.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.61.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.61.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.61.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.62.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.62.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.62.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.63.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.63.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.63.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.64.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.64.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.64.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.65.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.65.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.65.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.66.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.66.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.66.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.67.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.67.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.67.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.68.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.68.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.68.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.69.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.69.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.69.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.70.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.70.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.70.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.71.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.71.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.71.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.72.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.72.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.72.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.73.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.73.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.73.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.74.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.74.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.74.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.75.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.75.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.75.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.76.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.76.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.76.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.77.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.77.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.77.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.78.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.78.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.78.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.79.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.79.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.79.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.80.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.80.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.80.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.81.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.81.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.81.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.82.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.82.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.82.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.83.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.83.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.83.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.84.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.84.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.84.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.85.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.85.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.85.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.86.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.86.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.86.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.87.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.87.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.87.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.88.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.88.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.88.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.89.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.89.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.89.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.90.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.90.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.90.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.91.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.91.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.91.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.92.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.92.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.92.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.93.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.93.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.93.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.94.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.94.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.94.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.95.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.95.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.95.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.96.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.96.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.96.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.97.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.97.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.97.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.98.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.98.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.98.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.99.w1.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.99.w2.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.99.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00020.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.100.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.100.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.100.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.101.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.101.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.101.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.102.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.102.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.102.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.103.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.103.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.103.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.104.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.104.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.104.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.105.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.105.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.105.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.106.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.106.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.106.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.107.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.107.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.107.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.108.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.108.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.108.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.109.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.109.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.109.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.110.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.110.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.110.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.111.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.111.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.111.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.112.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.112.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.112.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.113.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.113.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.113.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.114.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.114.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.114.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.115.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.115.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.115.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.32.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.32.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.32.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.33.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.33.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.33.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.34.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.34.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.34.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.35.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.35.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.35.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.36.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.36.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.36.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.37.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.37.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.37.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.38.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.38.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.38.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.39.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.39.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.39.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.40.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.40.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.40.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.41.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.41.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.41.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.42.w1.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.42.w2.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.42.w3.weight": "model-00001-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.43.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.43.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.44.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.44.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.45.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.45.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.45.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.46.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.46.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.47.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.47.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.49.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.49.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.49.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.50.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.50.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.50.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.51.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.51.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.52.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.52.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.53.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.53.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.53.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.54.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.54.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.54.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.55.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.55.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.55.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.56.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.56.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.57.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.58.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.58.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.59.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.60.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.60.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.60.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.61.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.61.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.62.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.62.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.62.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.63.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.63.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.63.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.64.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.64.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.64.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.65.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.65.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.65.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.66.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.66.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.66.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.67.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.67.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.67.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.68.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.68.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.68.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.69.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.69.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.69.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.70.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.70.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.70.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.71.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.71.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.71.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.72.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.72.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.72.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.73.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.73.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.73.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.74.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.74.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.74.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.75.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.75.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.75.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.76.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.76.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.76.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.77.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.77.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.77.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.78.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.78.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.78.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.79.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.79.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.79.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.8.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.80.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.80.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.80.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.81.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.81.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.81.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.82.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.82.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.82.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.83.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.83.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.83.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.84.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.84.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.84.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.85.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.85.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.85.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.86.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.86.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.86.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.87.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.87.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.87.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.88.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.88.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.88.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.89.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.89.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.89.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.9.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.9.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.90.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.90.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.90.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.91.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.91.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.91.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.92.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.92.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.92.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.93.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.93.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.93.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.94.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.94.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.94.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.95.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.95.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.95.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.96.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.96.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.96.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.97.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.97.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.97.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.98.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.98.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.98.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.99.w1.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.99.w2.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.99.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00020.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.10.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.100.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.100.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.100.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.101.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.101.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.101.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.102.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.102.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.102.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.103.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.103.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.103.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.104.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.104.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.104.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.105.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.105.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.105.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.106.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.106.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.106.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.107.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.107.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.107.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.108.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.108.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.108.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.109.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.109.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.109.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.110.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.110.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.110.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.111.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.111.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.111.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.112.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.112.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.112.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.113.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.113.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.113.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.114.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.114.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.114.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.115.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.115.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.115.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.13.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.16.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.16.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.17.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.19.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.23.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.27.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.32.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.32.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.33.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.33.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.34.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.35.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.35.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.36.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.37.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.37.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.38.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.38.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.38.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.39.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.39.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.39.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.40.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.40.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.40.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.41.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.41.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.41.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.42.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.42.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.43.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.43.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.44.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.44.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.45.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.45.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.45.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.46.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.46.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.47.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.47.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.49.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.49.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.49.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.50.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.50.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.50.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.51.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.51.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.52.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.52.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.53.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.53.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.53.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.54.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.54.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.54.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.55.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.55.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.55.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.56.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.56.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.57.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.58.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.58.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.59.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.60.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.60.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.60.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.61.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.61.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.62.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.62.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.62.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.63.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.63.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.63.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.64.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.64.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.64.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.65.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.65.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.65.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.66.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.66.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.66.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.67.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.67.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.67.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.68.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.68.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.68.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.69.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.69.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.69.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.70.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.70.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.70.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.71.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.71.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.71.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.72.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.72.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.72.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.73.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.73.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.73.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.74.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.74.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.74.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.75.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.75.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.75.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.76.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.76.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.76.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.77.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.77.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.77.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.78.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.78.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.78.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.79.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.79.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.79.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.8.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.80.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.80.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.80.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.81.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.81.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.81.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.82.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.82.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.82.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.83.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.83.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.83.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.84.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.84.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.84.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.85.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.85.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.85.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.86.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.86.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.86.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.87.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.87.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.87.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.88.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.88.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.88.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.89.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.89.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.89.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.9.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.9.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.90.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.90.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.90.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.91.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.91.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.91.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.92.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.92.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.92.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.93.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.93.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.93.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.94.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.94.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.94.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.95.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.95.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.95.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.96.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.96.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.96.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.97.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.97.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.97.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.98.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.98.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.98.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.99.w1.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.99.w2.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.99.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00020.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00020.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00020.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.10.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.100.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.100.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.100.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.101.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.101.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.101.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.102.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.102.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.102.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.103.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.103.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.103.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.104.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.104.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.104.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.105.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.105.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.105.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.106.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.106.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.106.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.107.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.107.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.107.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.108.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.108.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.108.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.109.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.109.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.109.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.110.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.110.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.110.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.111.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.111.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.111.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.112.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.112.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.112.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.113.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.113.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.113.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.114.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.114.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.114.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.115.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.115.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.115.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.13.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.16.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.16.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.17.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.19.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.23.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.27.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.32.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.32.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.33.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.33.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.34.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.35.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.35.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.36.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.37.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.37.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.38.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.38.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.38.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.39.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.39.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.39.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.40.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.40.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.40.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.41.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.41.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.41.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.42.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.42.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.43.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.43.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.44.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.44.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.45.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.45.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.45.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.46.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.46.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.47.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.47.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.49.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.49.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.49.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.50.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.50.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.50.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.51.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.51.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.52.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.52.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.53.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.53.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.53.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.54.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.54.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.54.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.55.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.55.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.55.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.56.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.56.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.57.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.58.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.58.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.59.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.60.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.60.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.60.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.61.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.61.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.62.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.62.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.62.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.63.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.63.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.63.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.64.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.64.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.64.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.65.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.65.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.65.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.66.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.66.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.66.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.67.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.67.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.67.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.68.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.68.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.68.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.69.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.69.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.69.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.70.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.70.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.70.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.71.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.71.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.71.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.72.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.72.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.72.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.73.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.73.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.73.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.74.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.74.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.74.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.75.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.75.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.75.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.76.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.76.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.76.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.77.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.77.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.77.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.78.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.78.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.78.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.79.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.79.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.79.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.8.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.80.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.80.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.80.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.81.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.81.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.81.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.82.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.82.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.82.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.83.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.83.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.83.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.84.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.84.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.84.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.85.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.85.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.85.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.86.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.86.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.86.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.87.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.87.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.87.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.88.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.88.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.88.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.89.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.89.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.89.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.9.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.9.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.90.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.90.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.90.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.91.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.91.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.91.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.92.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.92.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.92.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.93.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.93.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.93.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.94.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.94.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.94.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.95.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.95.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.95.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.96.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.96.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.96.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.97.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.97.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.97.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.98.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.98.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.98.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.99.w1.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.99.w2.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.99.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00020.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.10.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.100.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.100.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.100.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.101.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.101.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.101.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.102.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.102.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.102.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.103.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.103.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.103.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.104.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.104.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.104.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.105.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.105.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.105.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.106.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.106.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.106.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.107.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.107.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.107.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.108.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.108.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.108.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.109.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.109.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.109.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.110.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.110.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.110.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.111.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.111.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.111.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.112.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.112.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.112.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.113.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.113.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.113.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.114.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.114.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.114.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.115.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.115.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.115.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.13.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.16.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.16.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.17.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.19.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.23.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.27.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.32.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.32.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.32.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.33.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.33.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.33.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.34.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.34.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.34.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.35.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.35.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.35.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.36.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.36.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.36.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.37.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.37.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.37.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.38.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.38.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.38.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.39.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.39.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.39.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.40.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.40.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.40.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.41.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.41.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.41.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.42.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.42.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.42.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.43.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.43.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.43.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.44.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.44.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.44.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.45.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.45.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.45.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.46.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.46.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.46.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.47.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.47.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.47.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.48.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.48.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.48.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.49.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.49.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.49.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.50.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.50.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.50.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.51.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.51.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.51.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.52.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.52.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.52.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.53.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.53.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.53.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.54.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.54.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.54.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.55.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.55.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.55.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.56.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.56.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.56.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.57.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.57.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.57.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.58.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.58.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.58.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.59.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.59.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.59.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.60.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.60.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.60.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.61.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.61.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.61.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.62.w1.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.62.w2.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.62.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.63.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.63.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.63.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.64.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.64.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.64.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.65.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.65.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.65.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.66.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.66.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.66.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.67.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.67.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.67.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.68.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.68.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.68.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.69.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.69.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.69.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.70.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.70.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.70.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.71.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.71.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.71.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.72.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.72.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.72.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.73.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.73.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.73.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.74.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.74.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.74.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.75.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.75.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.75.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.76.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.76.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.76.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.77.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.77.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.77.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.78.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.78.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.78.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.79.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.79.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.79.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.8.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.8.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.8.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.80.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.80.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.80.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.81.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.81.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.81.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.82.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.82.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.82.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.83.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.83.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.83.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.84.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.84.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.84.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.85.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.85.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.85.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.86.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.86.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.86.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.87.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.87.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.87.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.88.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.88.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.88.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.89.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.89.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.89.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.9.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.9.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.9.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.90.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.90.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.90.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.91.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.91.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.91.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.92.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.92.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.92.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.93.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.93.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.93.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.94.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.94.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.94.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.95.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.95.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.95.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.96.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.96.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.96.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.97.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.97.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.97.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.98.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.98.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.98.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.99.w1.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.99.w2.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.99.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00020.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00020.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00020.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.10.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.10.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.100.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.100.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.100.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.101.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.101.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.101.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.102.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.102.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.102.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.103.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.103.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.103.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.104.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.104.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.104.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.105.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.105.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.105.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.106.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.106.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.106.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.107.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.107.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.107.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.108.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.108.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.108.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.109.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.109.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.109.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.11.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.11.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.11.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.110.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.110.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.110.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.111.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.111.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.111.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.112.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.112.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.112.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.113.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.113.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.113.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.114.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.114.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.114.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.115.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.115.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.115.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.12.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.12.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.12.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.13.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.14.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.14.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.14.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.15.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.15.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.15.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.16.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.16.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.16.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.17.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.17.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.18.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.18.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.18.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.19.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.19.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.19.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.20.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.20.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.21.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.21.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.21.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.22.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.22.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.22.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.23.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.23.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.23.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.24.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.24.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.24.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.25.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.25.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.25.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.26.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.26.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.26.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.27.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.27.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.27.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.28.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.28.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.29.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.29.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.29.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.30.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.30.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.30.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.31.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.31.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.31.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.32.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.32.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.32.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.33.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.33.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.33.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.34.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.34.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.34.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.35.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.35.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.35.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.36.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.36.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.36.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.37.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.37.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.37.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.38.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.38.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.38.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.39.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.39.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.39.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.40.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.40.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.40.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.41.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.41.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.42.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.42.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.42.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.43.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.43.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.43.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.44.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.45.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.45.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.45.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.46.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.46.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.46.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.47.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.47.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.47.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.48.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.48.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.48.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.49.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.49.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.49.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.50.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.50.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.51.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.51.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.51.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.52.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.52.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.52.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.53.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.53.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.53.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.54.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.54.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.54.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.55.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.55.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.55.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.56.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.56.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.57.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.57.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.58.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.58.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.58.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.59.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.59.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.59.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.60.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.60.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.61.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.61.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.61.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.62.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.62.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.63.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.63.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.63.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.64.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.64.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.64.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.65.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.65.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.65.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.66.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.66.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.66.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.67.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.67.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.67.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.68.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.68.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.68.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.69.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.69.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.69.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.70.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.70.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.70.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.71.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.71.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.71.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.72.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.72.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.72.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.73.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.73.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.73.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.74.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.74.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.74.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.75.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.75.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.75.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.76.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.76.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.76.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.77.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.77.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.77.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.78.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.78.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.78.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.79.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.79.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.79.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.8.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.8.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.8.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.80.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.80.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.80.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.81.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.81.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.81.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.82.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.82.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.82.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.83.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.83.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.83.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.84.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.84.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.84.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.85.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.85.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.85.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.86.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.86.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.86.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.87.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.87.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.87.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.88.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.88.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.88.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.89.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.89.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.89.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.9.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.9.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.9.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.90.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.90.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.90.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.91.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.91.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.91.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.92.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.92.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.92.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.93.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.93.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.93.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.94.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.94.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.94.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.95.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.95.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.95.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.96.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.96.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.96.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.97.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.97.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.97.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.98.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.98.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.98.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.99.w1.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.99.w2.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.99.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00020.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00020.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00020.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.10.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.10.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.100.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.100.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.100.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.101.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.101.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.101.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.102.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.102.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.102.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.103.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.103.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.103.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.104.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.104.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.104.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.105.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.105.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.105.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.106.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.106.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.106.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.107.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.107.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.107.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.108.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.108.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.108.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.109.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.109.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.109.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.11.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.11.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.11.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.110.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.110.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.110.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.111.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.111.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.111.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.112.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.112.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.112.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.113.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.113.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.113.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.114.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.114.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.114.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.115.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.115.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.115.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.12.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.12.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.12.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.13.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.14.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.14.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.14.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.15.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.15.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.15.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.16.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.16.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.16.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.17.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.17.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.18.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.18.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.18.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.19.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.19.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.19.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.20.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.20.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.21.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.21.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.21.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.22.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.22.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.22.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.23.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.23.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.23.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.24.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.24.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.24.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.25.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.25.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.25.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.26.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.26.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.26.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.27.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.27.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.27.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.28.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.28.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.29.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.29.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.29.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.30.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.30.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.30.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.31.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.31.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.31.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.32.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.32.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.32.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.33.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.33.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.33.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.34.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.34.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.34.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.35.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.35.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.35.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.36.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.36.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.36.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.37.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.37.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.37.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.38.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.38.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.38.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.39.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.39.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.39.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.40.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.40.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.40.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.41.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.41.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.42.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.42.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.42.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.43.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.43.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.43.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.44.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.45.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.45.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.45.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.46.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.46.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.46.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.47.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.47.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.47.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.48.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.48.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.48.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.49.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.49.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.49.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.50.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.50.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.51.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.51.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.51.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.52.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.52.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.52.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.53.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.53.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.53.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.54.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.54.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.54.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.55.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.55.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.55.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.56.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.56.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.57.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.57.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.58.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.58.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.58.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.59.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.59.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.59.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.60.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.60.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.61.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.61.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.61.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.62.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.62.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.63.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.63.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.63.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.64.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.64.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.64.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.65.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.65.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.65.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.66.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.66.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.66.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.67.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.67.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.67.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.68.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.68.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.68.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.69.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.69.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.69.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.70.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.70.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.70.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.71.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.71.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.71.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.72.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.72.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.72.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.73.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.73.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.73.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.74.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.74.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.74.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.75.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.75.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.75.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.76.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.76.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.76.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.77.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.77.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.77.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.78.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.78.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.78.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.79.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.79.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.79.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.8.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.8.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.8.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.80.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.80.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.80.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.81.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.81.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.81.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.82.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.82.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.82.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.83.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.83.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.83.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.84.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.84.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.84.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.85.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.85.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.85.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.86.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.86.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.86.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.87.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.87.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.87.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.88.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.88.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.88.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.89.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.89.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.89.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.9.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.9.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.9.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.90.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.90.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.90.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.91.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.91.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.91.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.92.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.92.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.92.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.93.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.93.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.93.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.94.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.94.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.94.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.95.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.95.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.95.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.96.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.96.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.96.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.97.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.97.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.97.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.98.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.98.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.98.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.99.w1.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.99.w2.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.99.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00020.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00020.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00020.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.10.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.10.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.10.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.100.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.100.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.100.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.101.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.101.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.101.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.102.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.102.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.102.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.103.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.103.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.103.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.104.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.104.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.104.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.105.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.105.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.105.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.106.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.106.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.106.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.107.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.107.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.107.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.108.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.108.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.108.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.109.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.109.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.109.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.11.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.11.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.11.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.110.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.110.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.110.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.111.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.111.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.111.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.112.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.112.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.112.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.113.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.113.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.113.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.114.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.114.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.114.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.115.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.115.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.115.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.12.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.12.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.12.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.13.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.13.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.13.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.14.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.14.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.14.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.15.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.15.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.15.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.16.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.16.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.16.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.17.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.17.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.17.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.18.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.18.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.18.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.19.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.19.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.19.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.20.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.20.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.20.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.21.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.21.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.21.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.22.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.22.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.22.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.23.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.23.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.23.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.24.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.24.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.24.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.25.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.25.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.25.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.26.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.26.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.26.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.27.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.27.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.27.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.28.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.28.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.28.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.29.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.29.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.29.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.30.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.30.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.30.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.31.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.31.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.31.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.32.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.32.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.32.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.33.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.33.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.33.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.34.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.34.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.34.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.35.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.35.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.35.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.36.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.36.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.36.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.37.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.37.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.37.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.38.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.38.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.38.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.39.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.39.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.39.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.40.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.40.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.40.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.41.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.41.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.41.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.42.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.42.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.42.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.43.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.43.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.43.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.44.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.44.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.44.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.45.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.45.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.45.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.46.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.46.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.46.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.47.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.47.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.47.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.48.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.48.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.48.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.49.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.49.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.49.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.50.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.50.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.50.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.51.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.51.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.51.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.52.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.52.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.52.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.53.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.53.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.53.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.54.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.54.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.54.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.55.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.55.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.55.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.56.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.56.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.56.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.57.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.57.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.57.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.58.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.58.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.58.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.59.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.59.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.59.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.60.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.60.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.60.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.61.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.61.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.61.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.62.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.62.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.62.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.63.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.63.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.63.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.64.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.64.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.64.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.65.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.65.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.65.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.66.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.66.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.66.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.67.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.67.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.67.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.68.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.68.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.68.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.69.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.69.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.69.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.70.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.70.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.70.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.71.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.71.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.71.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.72.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.72.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.72.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.73.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.73.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.73.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.74.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.74.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.74.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.75.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.75.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.75.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.76.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.76.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.76.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.77.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.77.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.77.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.78.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.78.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.78.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.79.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.79.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.79.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.8.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.8.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.8.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.80.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.80.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.80.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.81.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.81.w2.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.81.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.82.w1.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.82.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.82.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.83.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.83.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.83.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.84.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.84.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.84.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.85.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.85.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.85.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.86.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.86.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.86.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.87.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.87.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.87.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.88.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.88.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.88.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.89.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.89.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.89.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.9.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.9.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.9.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.90.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.90.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.90.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.91.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.91.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.91.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.92.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.92.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.92.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.93.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.93.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.93.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.94.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.94.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.94.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.95.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.95.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.95.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.96.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.96.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.96.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.97.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.97.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.97.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.98.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.98.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.98.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.99.w1.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.99.w2.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.99.w3.weight": "model-00004-of-00020.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00004-of-00020.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00020.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00020.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.10.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.10.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.10.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.100.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.100.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.100.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.101.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.101.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.101.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.102.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.102.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.102.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.103.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.103.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.103.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.104.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.104.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.104.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.105.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.105.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.105.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.106.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.106.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.106.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.107.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.107.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.107.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.108.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.108.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.108.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.109.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.109.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.109.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.11.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.11.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.11.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.110.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.110.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.110.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.111.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.111.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.111.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.112.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.112.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.112.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.113.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.113.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.113.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.114.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.114.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.114.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.115.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.115.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.115.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.12.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.12.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.12.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.13.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.13.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.13.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.14.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.14.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.14.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.15.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.15.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.15.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.16.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.16.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.16.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.17.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.17.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.17.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.18.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.18.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.18.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.19.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.19.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.19.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.20.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.20.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.20.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.21.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.21.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.21.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.22.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.22.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.22.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.23.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.23.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.23.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.24.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.24.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.25.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.25.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.25.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.26.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.26.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.26.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.27.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.27.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.27.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.28.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.28.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.29.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.29.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.29.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.30.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.30.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.30.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.31.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.31.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.31.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.32.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.32.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.32.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.33.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.33.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.33.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.34.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.34.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.34.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.35.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.35.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.35.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.36.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.36.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.36.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.37.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.37.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.37.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.38.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.38.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.38.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.39.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.39.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.39.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.40.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.40.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.40.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.41.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.41.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.41.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.42.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.42.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.42.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.43.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.43.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.43.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.44.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.44.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.44.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.45.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.45.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.45.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.46.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.46.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.46.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.47.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.47.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.47.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.48.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.48.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.48.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.49.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.49.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.49.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.50.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.50.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.50.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.51.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.51.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.51.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.52.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.52.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.52.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.53.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.53.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.53.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.54.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.54.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.54.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.55.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.55.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.55.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.56.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.56.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.56.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.57.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.57.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.57.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.58.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.58.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.58.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.59.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.59.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.59.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.60.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.60.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.60.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.61.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.61.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.62.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.62.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.62.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.63.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.63.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.63.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.64.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.64.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.64.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.65.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.65.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.65.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.66.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.66.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.66.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.67.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.67.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.67.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.68.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.68.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.68.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.69.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.69.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.69.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.70.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.70.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.70.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.71.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.71.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.71.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.72.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.72.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.72.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.73.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.73.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.73.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.74.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.74.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.74.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.75.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.75.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.75.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.76.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.76.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.76.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.77.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.77.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.77.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.78.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.78.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.78.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.79.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.79.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.79.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.8.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.8.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.80.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.80.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.80.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.81.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.81.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.81.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.82.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.82.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.82.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.83.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.83.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.83.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.84.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.84.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.84.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.85.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.85.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.85.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.86.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.86.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.86.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.87.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.87.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.87.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.88.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.88.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.88.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.89.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.89.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.89.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.9.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.9.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.9.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.90.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.90.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.90.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.91.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.91.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.91.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.92.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.92.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.92.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.93.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.93.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.93.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.94.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.94.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.94.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.95.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.95.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.95.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.96.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.96.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.96.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.97.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.97.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.97.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.98.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.98.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.98.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.99.w1.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.99.w2.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.99.w3.weight": "model-00004-of-00020.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00004-of-00020.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00020.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00020.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.10.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.10.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.10.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.100.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.100.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.100.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.101.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.101.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.101.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.102.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.102.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.102.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.103.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.103.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.103.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.104.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.104.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.104.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.105.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.105.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.105.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.106.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.106.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.106.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.107.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.107.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.107.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.108.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.108.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.108.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.109.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.109.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.109.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.11.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.11.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.11.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.110.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.110.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.110.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.111.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.111.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.111.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.112.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.112.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.112.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.113.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.113.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.113.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.114.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.114.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.114.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.115.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.115.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.115.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.12.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.12.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.12.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.13.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.13.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.13.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.14.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.14.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.14.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.15.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.15.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.15.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.16.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.16.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.16.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.17.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.17.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.17.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.18.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.18.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.18.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.19.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.19.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.19.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.20.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.20.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.20.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.21.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.21.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.21.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.22.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.22.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.22.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.23.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.23.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.23.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.24.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.24.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.25.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.25.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.25.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.26.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.26.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.26.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.27.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.27.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.27.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.28.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.28.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.29.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.29.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.29.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.30.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.30.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.30.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.31.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.31.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.31.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.32.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.32.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.32.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.33.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.33.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.33.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.34.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.34.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.34.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.35.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.35.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.35.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.36.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.36.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.36.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.37.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.37.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.37.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.38.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.38.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.38.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.39.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.39.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.39.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.40.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.40.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.40.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.41.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.41.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.41.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.42.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.42.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.42.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.43.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.43.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.43.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.44.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.44.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.44.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.45.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.45.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.45.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.46.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.46.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.46.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.47.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.47.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.47.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.48.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.48.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.48.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.49.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.49.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.49.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.50.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.50.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.50.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.51.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.51.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.51.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.52.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.52.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.52.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.53.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.53.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.53.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.54.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.54.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.54.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.55.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.55.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.55.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.56.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.56.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.56.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.57.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.57.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.57.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.58.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.58.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.58.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.59.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.59.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.59.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.60.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.60.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.60.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.61.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.61.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.62.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.62.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.62.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.63.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.63.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.63.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.64.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.64.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.64.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.65.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.65.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.65.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.66.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.66.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.66.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.67.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.67.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.67.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.68.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.68.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.68.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.69.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.69.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.69.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.70.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.70.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.70.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.71.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.71.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.71.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.72.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.72.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.72.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.73.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.73.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.73.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.74.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.74.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.74.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.75.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.75.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.75.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.76.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.76.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.76.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.77.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.77.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.77.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.78.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.78.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.78.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.79.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.79.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.79.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.8.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.8.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.80.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.80.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.80.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.81.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.81.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.81.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.82.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.82.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.82.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.83.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.83.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.83.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.84.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.84.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.84.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.85.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.85.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.85.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.86.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.86.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.86.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.87.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.87.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.87.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.88.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.88.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.88.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.89.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.89.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.89.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.9.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.9.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.9.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.90.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.90.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.90.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.91.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.91.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.91.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.92.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.92.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.92.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.93.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.93.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.93.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.94.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.94.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.94.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.95.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.95.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.95.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.96.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.96.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.96.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.97.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.97.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.97.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.98.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.98.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.98.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.99.w1.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.99.w2.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.99.w3.weight": "model-00004-of-00020.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00004-of-00020.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00020.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00020.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.10.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.10.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.10.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.100.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.100.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.100.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.101.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.101.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.101.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.102.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.102.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.102.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.103.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.103.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.103.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.104.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.104.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.104.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.105.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.105.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.105.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.106.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.106.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.106.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.107.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.107.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.107.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.108.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.108.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.108.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.109.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.109.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.109.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.11.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.11.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.11.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.110.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.110.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.110.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.111.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.111.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.111.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.112.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.112.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.112.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.113.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.113.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.113.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.114.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.114.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.114.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.115.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.115.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.115.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.12.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.12.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.12.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.13.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.13.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.13.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.14.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.14.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.14.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.15.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.15.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.15.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.16.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.16.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.16.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.17.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.17.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.17.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.18.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.18.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.18.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.19.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.19.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.19.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.20.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.20.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.20.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.21.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.21.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.21.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.22.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.22.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.22.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.23.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.23.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.23.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.24.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.24.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.24.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.25.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.25.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.25.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.26.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.26.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.26.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.27.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.27.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.27.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.28.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.28.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.28.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.29.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.29.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.29.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.30.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.30.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.30.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.31.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.31.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.31.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.32.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.32.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.32.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.33.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.33.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.33.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.34.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.34.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.34.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.35.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.35.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.35.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.36.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.36.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.36.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.37.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.37.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.37.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.38.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.38.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.38.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.39.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.39.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.39.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.40.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.40.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.40.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.41.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.41.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.41.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.42.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.42.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.42.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.43.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.43.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.43.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.44.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.44.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.44.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.45.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.45.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.45.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.46.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.46.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.46.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.47.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.47.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.47.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.48.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.48.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.48.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.49.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.49.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.49.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.50.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.50.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.50.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.51.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.51.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.51.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.52.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.52.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.52.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.53.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.53.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.53.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.54.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.54.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.54.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.55.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.55.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.55.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.56.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.56.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.56.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.57.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.57.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.57.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.58.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.58.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.58.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.59.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.59.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.59.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.60.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.60.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.60.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.61.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.61.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.61.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.62.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.62.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.62.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.63.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.63.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.63.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.64.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.64.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.64.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.65.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.65.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.65.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.66.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.66.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.66.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.67.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.67.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.67.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.68.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.68.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.68.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.69.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.69.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.69.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.70.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.70.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.70.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.71.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.71.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.71.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.72.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.72.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.72.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.73.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.73.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.73.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.74.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.74.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.74.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.75.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.75.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.75.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.76.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.76.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.76.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.77.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.77.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.77.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.78.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.78.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.78.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.79.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.79.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.79.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.8.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.8.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.8.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.80.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.80.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.80.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.81.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.81.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.81.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.82.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.82.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.82.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.83.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.83.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.83.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.84.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.84.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.84.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.85.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.85.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.85.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.86.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.86.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.86.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.87.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.87.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.87.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.88.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.88.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.88.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.89.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.89.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.89.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.9.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.9.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.9.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.90.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.90.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.90.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.91.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.91.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.91.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.92.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.92.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.92.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.93.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.93.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.93.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.94.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.94.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.94.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.95.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.95.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.95.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.96.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.96.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.96.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.97.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.97.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.97.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.98.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.98.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.98.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.99.w1.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.99.w2.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.99.w3.weight": "model-00004-of-00020.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00020.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00020.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00020.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.10.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.10.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.100.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.100.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.100.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.101.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.101.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.101.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.102.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.102.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.102.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.103.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.103.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.103.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.104.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.104.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.104.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.105.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.105.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.105.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.106.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.106.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.106.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.107.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.107.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.107.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.108.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.108.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.108.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.109.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.109.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.109.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.11.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.11.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.11.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.110.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.110.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.110.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.111.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.111.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.111.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.112.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.112.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.112.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.113.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.113.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.113.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.114.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.114.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.114.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.115.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.115.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.115.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.12.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.12.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.12.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.13.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.13.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.13.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.14.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.14.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.14.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.15.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.15.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.15.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.16.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.16.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.17.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.17.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.18.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.18.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.18.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.19.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.19.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.19.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.20.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.20.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.21.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.21.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.21.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.22.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.22.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.22.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.23.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.23.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.23.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.24.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.24.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.24.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.25.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.25.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.25.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.26.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.26.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.26.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.27.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.27.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.27.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.28.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.28.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.28.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.29.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.29.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.29.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.30.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.30.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.30.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.31.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.31.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.31.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.32.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.32.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.32.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.33.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.33.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.33.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.34.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.34.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.34.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.35.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.35.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.35.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.36.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.36.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.36.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.37.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.37.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.37.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.38.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.38.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.38.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.39.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.39.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.40.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.40.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.40.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.41.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.41.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.42.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.42.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.43.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.43.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.43.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.44.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.44.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.44.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.45.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.45.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.46.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.46.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.46.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.47.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.48.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.48.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.48.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.49.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.49.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.50.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.50.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.50.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.51.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.51.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.51.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.52.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.52.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.52.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.53.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.53.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.53.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.54.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.54.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.54.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.55.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.55.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.55.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.56.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.56.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.56.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.57.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.57.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.57.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.58.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.58.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.58.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.59.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.59.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.59.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.60.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.60.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.61.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.61.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.61.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.62.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.62.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.62.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.63.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.63.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.64.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.64.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.64.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.65.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.65.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.65.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.66.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.66.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.66.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.67.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.67.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.67.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.68.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.68.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.68.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.69.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.69.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.69.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.70.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.70.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.70.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.71.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.71.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.71.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.72.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.72.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.72.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.73.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.73.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.73.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.74.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.74.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.74.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.75.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.75.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.75.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.76.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.76.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.76.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.77.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.77.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.77.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.78.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.78.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.78.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.79.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.79.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.79.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.8.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.8.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.8.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.80.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.80.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.80.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.81.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.81.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.81.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.82.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.82.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.82.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.83.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.83.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.83.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.84.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.84.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.84.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.85.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.85.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.85.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.86.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.86.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.86.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.87.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.87.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.87.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.88.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.88.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.88.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.89.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.89.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.89.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.9.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.9.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.9.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.90.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.90.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.90.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.91.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.91.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.91.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.92.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.92.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.92.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.93.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.93.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.93.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.94.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.94.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.94.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.95.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.95.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.95.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.96.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.96.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.96.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.97.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.97.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.97.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.98.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.98.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.98.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.99.w1.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.99.w2.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.99.w3.weight": "model-00005-of-00020.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00005-of-00020.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.2.self_attn.k_norm.weight": "model-00005-of-00020.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.2.self_attn.q_norm.weight": "model-00005-of-00020.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.10.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.10.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.100.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.100.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.100.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.101.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.101.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.101.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.102.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.102.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.102.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.103.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.103.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.103.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.104.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.104.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.104.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.105.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.105.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.105.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.106.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.106.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.106.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.107.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.107.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.107.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.108.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.108.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.108.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.109.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.109.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.109.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.11.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.11.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.11.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.110.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.110.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.110.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.111.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.111.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.111.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.112.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.112.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.112.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.113.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.113.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.113.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.114.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.114.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.114.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.115.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.115.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.115.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.12.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.12.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.12.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.13.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.13.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.13.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.14.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.14.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.14.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.15.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.15.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.15.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.16.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.16.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.17.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.17.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.18.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.18.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.18.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.19.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.19.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.19.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.20.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.20.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.21.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.21.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.21.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.22.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.22.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.22.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.23.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.23.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.23.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.24.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.24.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.24.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.25.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.25.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.25.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.26.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.26.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.26.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.27.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.27.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.27.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.28.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.28.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.28.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.29.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.29.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.29.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.30.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.30.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.30.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.31.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.31.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.31.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.32.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.32.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.32.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.33.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.33.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.33.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.34.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.34.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.34.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.35.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.35.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.35.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.36.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.36.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.36.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.37.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.37.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.37.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.38.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.38.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.38.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.39.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.39.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.40.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.40.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.40.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.41.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.41.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.42.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.42.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.43.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.43.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.43.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.44.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.44.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.44.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.45.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.45.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.46.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.46.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.46.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.47.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.48.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.48.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.48.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.49.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.49.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.50.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.50.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.50.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.51.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.51.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.51.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.52.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.52.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.52.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.53.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.53.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.53.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.54.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.54.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.54.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.55.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.55.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.55.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.56.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.56.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.56.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.57.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.57.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.57.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.58.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.58.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.58.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.59.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.59.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.59.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.60.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.60.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.61.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.61.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.61.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.62.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.62.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.62.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.63.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.63.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.64.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.64.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.64.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.65.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.65.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.65.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.66.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.66.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.66.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.67.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.67.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.67.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.68.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.68.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.68.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.69.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.69.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.69.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.70.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.70.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.70.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.71.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.71.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.71.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.72.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.72.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.72.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.73.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.73.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.73.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.74.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.74.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.74.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.75.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.75.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.75.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.76.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.76.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.76.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.77.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.77.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.77.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.78.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.78.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.78.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.79.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.79.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.79.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.8.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.8.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.8.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.80.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.80.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.80.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.81.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.81.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.81.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.82.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.82.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.82.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.83.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.83.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.83.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.84.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.84.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.84.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.85.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.85.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.85.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.86.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.86.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.86.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.87.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.87.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.87.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.88.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.88.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.88.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.89.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.89.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.89.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.9.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.9.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.9.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.90.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.90.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.90.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.91.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.91.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.91.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.92.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.92.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.92.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.93.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.93.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.93.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.94.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.94.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.94.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.95.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.95.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.95.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.96.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.96.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.96.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.97.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.97.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.97.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.98.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.98.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.98.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.99.w1.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.99.w2.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.99.w3.weight": "model-00005-of-00020.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00005-of-00020.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.20.self_attn.k_norm.weight": "model-00005-of-00020.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.20.self_attn.q_norm.weight": "model-00005-of-00020.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.10.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.10.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.100.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.100.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.100.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.101.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.101.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.101.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.102.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.102.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.102.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.103.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.103.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.103.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.104.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.104.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.104.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.105.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.105.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.105.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.106.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.106.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.106.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.107.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.107.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.107.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.108.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.108.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.108.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.109.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.109.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.109.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.11.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.11.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.11.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.110.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.110.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.110.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.111.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.111.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.111.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.112.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.112.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.112.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.113.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.113.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.113.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.114.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.114.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.114.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.115.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.115.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.115.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.12.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.12.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.12.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.13.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.13.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.13.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.14.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.14.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.14.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.15.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.15.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.15.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.16.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.16.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.16.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.17.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.17.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.17.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.18.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.18.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.18.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.19.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.19.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.19.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.20.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.20.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.20.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.21.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.21.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.21.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.22.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.22.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.22.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.23.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.23.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.23.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.24.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.24.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.24.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.25.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.25.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.25.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.26.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.26.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.26.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.27.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.27.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.27.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.28.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.28.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.28.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.29.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.29.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.29.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.30.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.30.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.30.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.31.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.31.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.31.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.32.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.32.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.32.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.33.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.33.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.33.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.34.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.34.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.34.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.35.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.35.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.35.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.36.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.36.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.36.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.37.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.37.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.37.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.38.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.38.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.38.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.39.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.39.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.39.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.40.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.40.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.40.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.41.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.41.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.41.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.42.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.42.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.42.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.43.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.43.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.43.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.44.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.44.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.44.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.45.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.45.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.45.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.46.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.46.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.46.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.47.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.47.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.47.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.48.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.48.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.48.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.49.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.49.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.49.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.50.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.50.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.50.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.51.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.51.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.51.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.52.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.52.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.52.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.53.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.53.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.53.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.54.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.54.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.54.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.55.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.55.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.55.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.56.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.56.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.56.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.57.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.57.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.57.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.58.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.58.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.58.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.59.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.59.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.59.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.60.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.60.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.60.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.61.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.61.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.61.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.62.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.62.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.62.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.63.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.63.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.63.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.64.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.64.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.64.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.65.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.65.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.65.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.66.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.66.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.66.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.67.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.67.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.67.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.68.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.68.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.68.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.69.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.69.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.69.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.70.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.70.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.70.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.71.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.71.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.71.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.72.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.72.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.72.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.73.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.73.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.73.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.74.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.74.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.74.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.75.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.75.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.75.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.76.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.76.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.76.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.77.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.77.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.77.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.78.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.78.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.78.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.79.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.79.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.79.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.8.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.8.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.8.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.80.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.80.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.80.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.81.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.81.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.81.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.82.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.82.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.82.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.83.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.83.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.83.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.84.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.84.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.84.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.85.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.85.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.85.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.86.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.86.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.86.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.87.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.87.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.87.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.88.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.88.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.88.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.89.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.89.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.89.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.9.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.9.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.9.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.90.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.90.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.90.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.91.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.91.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.91.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.92.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.92.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.92.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.93.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.93.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.93.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.94.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.94.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.94.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.95.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.95.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.95.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.96.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.96.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.96.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.97.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.97.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.97.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.98.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.98.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.98.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.99.w1.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.99.w2.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.99.w3.weight": "model-00005-of-00020.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00005-of-00020.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.21.self_attn.k_norm.weight": "model-00005-of-00020.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.21.self_attn.q_norm.weight": "model-00005-of-00020.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.10.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.10.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.10.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.100.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.100.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.100.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.101.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.101.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.101.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.102.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.102.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.102.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.103.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.103.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.103.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.104.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.104.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.104.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.105.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.105.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.105.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.106.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.106.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.106.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.107.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.107.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.107.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.108.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.108.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.108.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.109.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.109.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.109.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.11.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.11.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.11.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.110.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.110.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.110.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.111.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.111.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.111.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.112.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.112.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.112.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.113.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.113.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.113.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.114.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.114.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.114.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.115.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.115.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.115.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.12.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.12.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.12.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.13.w1.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.13.w2.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.14.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.14.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.15.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.15.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.15.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.16.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.16.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.16.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.17.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.17.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.17.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.18.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.18.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.18.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.19.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.20.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.20.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.20.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.21.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.21.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.21.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.22.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.22.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.22.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.23.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.23.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.23.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.24.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.24.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.24.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.25.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.25.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.26.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.26.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.26.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.27.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.27.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.27.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.28.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.28.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.28.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.29.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.29.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.29.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.30.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.30.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.30.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.31.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.31.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.31.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.32.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.32.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.32.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.33.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.33.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.33.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.34.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.34.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.35.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.35.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.35.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.36.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.36.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.36.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.37.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.37.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.37.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.38.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.38.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.39.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.39.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.39.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.40.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.40.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.40.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.41.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.41.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.41.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.42.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.42.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.42.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.43.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.43.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.43.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.44.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.44.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.44.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.45.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.45.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.45.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.46.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.46.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.46.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.47.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.47.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.47.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.48.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.48.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.48.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.49.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.49.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.50.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.50.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.50.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.51.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.51.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.51.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.52.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.52.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.52.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.53.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.54.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.54.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.54.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.55.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.55.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.55.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.56.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.56.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.56.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.57.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.57.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.58.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.58.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.58.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.59.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.59.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.59.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.60.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.60.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.60.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.61.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.61.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.61.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.62.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.62.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.62.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.63.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.63.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.63.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.64.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.64.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.64.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.65.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.65.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.65.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.66.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.66.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.66.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.67.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.67.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.67.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.68.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.68.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.68.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.69.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.69.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.69.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.70.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.70.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.70.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.71.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.71.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.71.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.72.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.72.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.72.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.73.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.73.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.73.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.74.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.74.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.74.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.75.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.75.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.75.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.76.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.76.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.76.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.77.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.77.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.77.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.78.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.78.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.78.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.79.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.79.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.79.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.8.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.8.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.80.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.80.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.80.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.81.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.81.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.81.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.82.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.82.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.82.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.83.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.83.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.83.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.84.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.84.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.84.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.85.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.85.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.85.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.86.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.86.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.86.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.87.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.87.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.87.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.88.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.88.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.88.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.89.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.89.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.89.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.9.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.90.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.90.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.90.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.91.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.91.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.91.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.92.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.92.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.92.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.93.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.93.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.93.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.94.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.94.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.94.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.95.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.95.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.95.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.96.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.96.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.96.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.97.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.97.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.97.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.98.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.98.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.98.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.99.w1.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.99.w2.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.99.w3.weight": "model-00006-of-00020.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00006-of-00020.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.22.self_attn.k_norm.weight": "model-00006-of-00020.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.22.self_attn.q_norm.weight": "model-00006-of-00020.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.10.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.10.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.100.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.100.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.100.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.101.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.101.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.101.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.102.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.102.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.102.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.103.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.103.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.103.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.104.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.104.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.104.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.105.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.105.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.105.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.106.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.106.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.106.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.107.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.107.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.107.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.108.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.108.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.108.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.109.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.109.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.109.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.11.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.11.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.11.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.110.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.110.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.110.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.111.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.111.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.111.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.112.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.112.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.112.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.113.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.113.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.113.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.114.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.114.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.114.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.115.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.115.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.115.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.12.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.12.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.12.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.13.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.13.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.14.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.14.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.15.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.15.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.15.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.16.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.16.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.16.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.17.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.17.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.17.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.18.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.18.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.18.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.19.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.20.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.20.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.20.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.21.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.21.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.21.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.22.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.22.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.22.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.23.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.23.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.23.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.24.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.24.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.24.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.25.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.25.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.26.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.26.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.26.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.27.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.27.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.27.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.28.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.28.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.28.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.29.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.29.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.29.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.30.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.30.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.30.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.31.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.31.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.31.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.32.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.32.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.32.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.33.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.33.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.33.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.34.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.34.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.35.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.35.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.35.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.36.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.36.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.36.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.37.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.37.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.37.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.38.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.38.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.39.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.39.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.39.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.40.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.40.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.40.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.41.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.41.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.41.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.42.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.42.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.42.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.43.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.43.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.43.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.44.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.44.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.44.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.45.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.45.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.45.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.46.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.46.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.46.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.47.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.47.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.47.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.48.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.48.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.48.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.49.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.49.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.50.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.50.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.50.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.51.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.51.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.51.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.52.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.52.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.52.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.53.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.54.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.54.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.54.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.55.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.55.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.55.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.56.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.56.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.56.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.57.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.57.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.58.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.58.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.58.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.59.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.59.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.59.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.60.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.60.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.60.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.61.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.61.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.61.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.62.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.62.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.62.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.63.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.63.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.63.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.64.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.64.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.64.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.65.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.65.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.65.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.66.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.66.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.66.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.67.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.67.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.67.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.68.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.68.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.68.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.69.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.69.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.69.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.70.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.70.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.70.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.71.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.71.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.71.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.72.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.72.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.72.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.73.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.73.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.73.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.74.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.74.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.74.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.75.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.75.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.75.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.76.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.76.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.76.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.77.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.77.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.77.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.78.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.78.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.78.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.79.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.79.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.79.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.8.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.8.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.80.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.80.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.80.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.81.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.81.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.81.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.82.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.82.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.82.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.83.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.83.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.83.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.84.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.84.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.84.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.85.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.85.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.85.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.86.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.86.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.86.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.87.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.87.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.87.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.88.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.88.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.88.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.89.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.89.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.89.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.9.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.90.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.90.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.90.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.91.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.91.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.91.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.92.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.92.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.92.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.93.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.93.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.93.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.94.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.94.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.94.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.95.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.95.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.95.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.96.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.96.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.96.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.97.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.97.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.97.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.98.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.98.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.98.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.99.w1.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.99.w2.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.99.w3.weight": "model-00006-of-00020.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00006-of-00020.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.23.self_attn.k_norm.weight": "model-00006-of-00020.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.23.self_attn.q_norm.weight": "model-00006-of-00020.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.10.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.10.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.100.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.100.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.100.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.101.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.101.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.101.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.102.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.102.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.102.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.103.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.103.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.103.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.104.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.104.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.104.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.105.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.105.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.105.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.106.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.106.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.106.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.107.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.107.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.107.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.108.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.108.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.108.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.109.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.109.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.109.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.11.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.11.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.11.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.110.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.110.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.110.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.111.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.111.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.111.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.112.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.112.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.112.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.113.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.113.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.113.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.114.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.114.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.114.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.115.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.115.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.115.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.12.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.12.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.12.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.13.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.13.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.14.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.14.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.15.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.15.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.15.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.16.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.16.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.16.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.17.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.17.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.17.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.18.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.18.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.18.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.19.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.20.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.20.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.20.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.21.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.21.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.21.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.22.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.22.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.22.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.23.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.23.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.23.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.24.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.24.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.24.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.25.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.25.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.26.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.26.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.26.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.27.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.27.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.27.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.28.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.28.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.28.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.29.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.29.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.29.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.30.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.30.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.30.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.31.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.31.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.31.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.32.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.32.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.32.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.33.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.33.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.33.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.34.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.34.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.34.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.35.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.35.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.35.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.36.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.36.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.36.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.37.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.37.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.37.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.38.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.38.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.38.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.39.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.39.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.39.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.40.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.40.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.40.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.41.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.41.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.41.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.42.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.42.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.42.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.43.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.43.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.43.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.44.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.44.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.44.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.45.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.45.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.45.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.46.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.46.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.46.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.47.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.47.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.47.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.48.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.48.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.48.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.49.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.49.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.49.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.50.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.50.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.50.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.51.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.51.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.51.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.52.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.52.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.52.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.53.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.53.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.53.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.54.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.54.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.54.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.55.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.55.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.55.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.56.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.56.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.56.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.57.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.57.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.57.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.58.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.58.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.58.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.59.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.59.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.59.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.60.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.60.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.60.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.61.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.61.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.61.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.62.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.62.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.62.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.63.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.63.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.63.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.64.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.64.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.64.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.65.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.65.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.65.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.66.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.66.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.66.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.67.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.67.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.67.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.68.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.68.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.68.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.69.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.69.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.69.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.70.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.70.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.70.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.71.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.71.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.71.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.72.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.72.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.72.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.73.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.73.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.73.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.74.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.74.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.74.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.75.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.75.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.75.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.76.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.76.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.76.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.77.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.77.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.77.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.78.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.78.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.78.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.79.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.79.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.79.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.8.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.8.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.8.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.80.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.80.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.80.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.81.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.81.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.81.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.82.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.82.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.82.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.83.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.83.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.83.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.84.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.84.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.84.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.85.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.85.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.85.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.86.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.86.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.86.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.87.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.87.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.87.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.88.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.88.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.88.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.89.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.89.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.89.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.9.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.9.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.9.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.90.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.90.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.90.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.91.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.91.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.91.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.92.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.92.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.92.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.93.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.93.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.93.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.94.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.94.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.94.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.95.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.95.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.95.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.96.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.96.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.96.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.97.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.97.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.97.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.98.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.98.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.98.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.99.w1.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.99.w2.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.99.w3.weight": "model-00006-of-00020.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00006-of-00020.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.24.self_attn.k_norm.weight": "model-00006-of-00020.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.24.self_attn.q_norm.weight": "model-00006-of-00020.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.10.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.10.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.10.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.100.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.100.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.100.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.101.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.101.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.101.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.102.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.102.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.102.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.103.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.103.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.103.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.104.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.104.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.104.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.105.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.105.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.105.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.106.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.106.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.106.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.107.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.107.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.107.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.108.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.108.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.108.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.109.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.109.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.109.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.11.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.11.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.11.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.110.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.110.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.110.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.111.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.111.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.111.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.112.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.112.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.112.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.113.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.113.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.113.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.114.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.114.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.114.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.115.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.115.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.115.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.12.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.12.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.12.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.13.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.13.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.13.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.14.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.14.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.14.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.15.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.15.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.15.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.16.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.16.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.16.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.17.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.17.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.17.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.18.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.18.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.18.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.19.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.19.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.19.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.20.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.20.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.20.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.21.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.21.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.21.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.22.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.22.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.22.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.23.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.23.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.23.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.24.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.24.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.24.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.25.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.25.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.25.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.26.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.26.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.26.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.27.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.27.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.27.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.28.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.28.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.28.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.29.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.29.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.29.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.30.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.30.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.30.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.31.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.31.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.31.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.32.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.32.w2.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.32.w3.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.33.w1.weight": "model-00006-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.33.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.33.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.34.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.34.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.34.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.35.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.35.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.35.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.36.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.36.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.36.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.37.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.37.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.37.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.38.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.38.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.38.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.39.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.39.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.39.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.40.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.40.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.40.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.41.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.41.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.41.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.42.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.42.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.42.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.43.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.43.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.43.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.44.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.44.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.44.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.45.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.45.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.45.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.46.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.46.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.46.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.47.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.47.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.47.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.48.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.48.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.48.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.49.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.49.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.49.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.50.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.50.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.50.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.51.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.51.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.51.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.52.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.52.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.52.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.53.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.53.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.53.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.54.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.54.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.54.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.55.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.55.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.55.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.56.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.56.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.56.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.57.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.57.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.57.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.58.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.58.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.58.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.59.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.59.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.59.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.60.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.60.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.60.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.61.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.61.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.61.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.62.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.62.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.62.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.63.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.63.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.63.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.64.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.64.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.64.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.65.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.65.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.65.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.66.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.66.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.66.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.67.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.67.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.67.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.68.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.68.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.68.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.69.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.69.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.69.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.70.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.70.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.70.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.71.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.71.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.71.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.72.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.72.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.72.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.73.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.73.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.73.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.74.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.74.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.74.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.75.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.75.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.75.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.76.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.76.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.76.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.77.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.77.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.77.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.78.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.78.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.78.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.79.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.79.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.79.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.8.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.8.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.8.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.80.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.80.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.80.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.81.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.81.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.81.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.82.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.82.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.82.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.83.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.83.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.83.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.84.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.84.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.84.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.85.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.85.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.85.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.86.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.86.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.86.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.87.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.87.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.87.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.88.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.88.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.88.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.89.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.89.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.89.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.9.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.9.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.9.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.90.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.90.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.90.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.91.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.91.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.91.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.92.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.92.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.92.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.93.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.93.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.93.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.94.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.94.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.94.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.95.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.95.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.95.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.96.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.96.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.96.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.97.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.97.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.97.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.98.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.98.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.98.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.99.w1.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.99.w2.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.99.w3.weight": "model-00007-of-00020.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00007-of-00020.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.25.self_attn.k_norm.weight": "model-00007-of-00020.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.25.self_attn.q_norm.weight": "model-00007-of-00020.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.10.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.10.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.100.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.100.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.100.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.101.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.101.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.101.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.102.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.102.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.102.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.103.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.103.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.103.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.104.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.104.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.104.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.105.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.105.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.105.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.106.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.106.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.106.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.107.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.107.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.107.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.108.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.108.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.108.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.109.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.109.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.109.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.11.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.11.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.11.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.110.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.110.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.110.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.111.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.111.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.111.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.112.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.112.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.112.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.113.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.113.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.113.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.114.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.114.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.114.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.115.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.115.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.115.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.12.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.12.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.12.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.13.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.13.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.13.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.14.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.14.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.14.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.15.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.15.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.15.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.16.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.16.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.16.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.17.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.17.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.17.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.18.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.18.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.18.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.19.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.19.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.19.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.20.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.20.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.20.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.21.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.21.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.21.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.22.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.22.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.22.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.23.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.23.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.23.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.24.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.24.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.24.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.25.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.25.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.25.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.26.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.26.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.26.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.27.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.27.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.27.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.28.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.28.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.28.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.29.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.29.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.29.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.30.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.30.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.30.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.31.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.31.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.31.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.32.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.32.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.32.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.33.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.33.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.33.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.34.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.34.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.34.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.35.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.35.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.35.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.36.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.36.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.36.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.37.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.37.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.37.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.38.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.38.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.38.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.39.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.39.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.39.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.40.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.40.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.40.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.41.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.41.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.41.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.42.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.42.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.42.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.43.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.43.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.43.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.44.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.44.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.44.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.45.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.45.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.45.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.46.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.46.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.46.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.47.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.47.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.47.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.48.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.48.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.48.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.49.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.49.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.49.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.50.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.50.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.50.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.51.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.51.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.51.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.52.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.52.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.52.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.53.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.53.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.53.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.54.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.54.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.54.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.55.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.55.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.55.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.56.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.56.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.56.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.57.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.57.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.57.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.58.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.58.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.58.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.59.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.59.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.59.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.60.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.60.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.60.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.61.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.61.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.61.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.62.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.62.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.62.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.63.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.63.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.63.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.64.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.64.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.64.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.65.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.65.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.65.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.66.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.66.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.66.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.67.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.67.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.67.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.68.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.68.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.68.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.69.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.69.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.69.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.70.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.70.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.70.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.71.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.71.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.71.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.72.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.72.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.72.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.73.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.73.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.73.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.74.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.74.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.74.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.75.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.75.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.75.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.76.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.76.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.76.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.77.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.77.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.77.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.78.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.78.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.78.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.79.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.79.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.79.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.8.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.8.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.8.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.80.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.80.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.80.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.81.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.81.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.81.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.82.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.82.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.82.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.83.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.83.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.83.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.84.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.84.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.84.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.85.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.85.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.85.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.86.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.86.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.86.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.87.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.87.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.87.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.88.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.88.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.88.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.89.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.89.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.89.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.9.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.9.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.9.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.90.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.90.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.90.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.91.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.91.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.91.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.92.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.92.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.92.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.93.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.93.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.93.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.94.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.94.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.94.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.95.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.95.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.95.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.96.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.96.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.96.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.97.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.97.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.97.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.98.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.98.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.98.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.99.w1.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.99.w2.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.99.w3.weight": "model-00007-of-00020.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00007-of-00020.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.26.self_attn.k_norm.weight": "model-00007-of-00020.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.26.self_attn.q_norm.weight": "model-00007-of-00020.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.10.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.10.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.100.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.100.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.100.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.101.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.101.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.101.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.102.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.102.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.102.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.103.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.103.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.103.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.104.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.104.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.104.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.105.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.105.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.105.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.106.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.106.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.106.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.107.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.107.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.107.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.108.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.108.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.108.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.109.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.109.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.109.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.11.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.11.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.11.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.110.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.110.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.110.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.111.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.111.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.111.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.112.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.112.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.112.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.113.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.113.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.113.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.114.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.114.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.114.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.115.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.115.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.115.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.12.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.12.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.12.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.13.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.13.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.13.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.14.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.14.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.14.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.15.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.15.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.15.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.16.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.16.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.16.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.17.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.17.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.17.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.18.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.18.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.18.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.19.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.19.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.19.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.20.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.20.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.20.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.21.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.21.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.21.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.22.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.22.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.22.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.23.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.23.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.23.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.24.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.24.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.24.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.25.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.25.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.25.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.26.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.26.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.26.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.27.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.27.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.27.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.28.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.28.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.28.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.29.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.29.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.29.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.30.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.30.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.30.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.31.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.31.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.31.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.32.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.32.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.32.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.33.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.33.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.33.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.34.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.34.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.34.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.35.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.35.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.35.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.36.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.36.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.36.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.37.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.37.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.37.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.38.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.38.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.38.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.39.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.39.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.39.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.40.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.40.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.40.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.41.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.41.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.41.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.42.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.42.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.42.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.43.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.43.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.43.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.44.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.44.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.44.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.45.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.45.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.45.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.46.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.46.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.46.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.47.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.47.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.47.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.48.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.48.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.48.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.49.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.49.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.49.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.50.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.50.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.50.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.51.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.51.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.51.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.52.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.52.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.52.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.53.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.53.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.53.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.54.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.54.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.54.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.55.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.55.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.55.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.56.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.56.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.56.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.57.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.57.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.57.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.58.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.58.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.58.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.59.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.59.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.59.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.60.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.60.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.60.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.61.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.61.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.61.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.62.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.62.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.62.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.63.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.63.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.63.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.64.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.64.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.64.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.65.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.65.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.65.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.66.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.66.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.66.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.67.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.67.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.67.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.68.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.68.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.68.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.69.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.69.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.69.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.70.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.70.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.70.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.71.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.71.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.71.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.72.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.72.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.72.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.73.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.73.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.73.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.74.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.74.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.74.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.75.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.75.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.75.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.76.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.76.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.76.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.77.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.77.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.77.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.78.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.78.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.78.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.79.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.79.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.79.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.8.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.8.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.8.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.80.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.80.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.80.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.81.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.81.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.81.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.82.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.82.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.82.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.83.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.83.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.83.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.84.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.84.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.84.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.85.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.85.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.85.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.86.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.86.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.86.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.87.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.87.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.87.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.88.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.88.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.88.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.89.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.89.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.89.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.9.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.9.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.9.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.90.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.90.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.90.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.91.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.91.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.91.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.92.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.92.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.92.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.93.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.93.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.93.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.94.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.94.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.94.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.95.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.95.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.95.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.96.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.96.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.96.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.97.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.97.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.97.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.98.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.98.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.98.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.99.w1.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.99.w2.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.99.w3.weight": "model-00007-of-00020.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00007-of-00020.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.27.self_attn.k_norm.weight": "model-00007-of-00020.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.27.self_attn.q_norm.weight": "model-00007-of-00020.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.10.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.10.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.10.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.100.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.100.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.100.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.101.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.101.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.101.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.102.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.102.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.102.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.103.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.103.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.103.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.104.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.104.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.104.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.105.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.105.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.105.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.106.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.106.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.106.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.107.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.107.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.107.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.108.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.108.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.108.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.109.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.109.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.109.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.11.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.11.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.11.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.110.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.110.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.110.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.111.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.111.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.111.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.112.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.112.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.112.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.113.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.113.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.113.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.114.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.114.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.114.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.115.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.115.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.115.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.12.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.12.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.12.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.13.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.13.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.13.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.14.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.14.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.14.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.15.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.15.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.15.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.16.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.16.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.16.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.17.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.17.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.17.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.18.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.18.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.18.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.19.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.19.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.19.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.20.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.20.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.20.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.21.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.21.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.21.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.22.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.22.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.22.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.23.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.23.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.23.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.24.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.24.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.24.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.25.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.25.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.25.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.26.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.26.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.26.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.27.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.27.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.27.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.28.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.28.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.28.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.29.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.29.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.29.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.30.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.30.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.30.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.31.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.31.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.31.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.32.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.32.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.32.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.33.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.33.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.33.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.34.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.34.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.34.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.35.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.35.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.35.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.36.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.36.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.36.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.37.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.37.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.37.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.38.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.38.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.38.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.39.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.39.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.39.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.40.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.40.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.40.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.41.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.41.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.41.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.42.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.42.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.42.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.43.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.43.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.43.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.44.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.44.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.44.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.45.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.45.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.45.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.46.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.46.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.46.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.47.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.47.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.47.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.48.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.48.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.48.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.49.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.49.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.49.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.50.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.50.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.50.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.51.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.51.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.51.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.52.w1.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.52.w2.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.52.w3.weight": "model-00007-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.53.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.53.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.53.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.54.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.54.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.54.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.55.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.55.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.55.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.56.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.56.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.56.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.57.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.57.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.57.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.58.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.58.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.58.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.59.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.59.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.59.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.60.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.60.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.60.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.61.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.61.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.61.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.62.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.62.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.62.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.63.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.63.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.63.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.64.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.64.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.64.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.65.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.65.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.65.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.66.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.66.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.66.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.67.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.67.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.67.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.68.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.68.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.68.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.69.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.69.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.69.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.70.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.70.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.70.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.71.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.71.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.71.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.72.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.72.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.72.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.73.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.73.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.73.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.74.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.74.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.74.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.75.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.75.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.75.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.76.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.76.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.76.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.77.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.77.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.77.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.78.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.78.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.78.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.79.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.79.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.79.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.8.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.8.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.8.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.80.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.80.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.80.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.81.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.81.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.81.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.82.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.82.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.82.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.83.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.83.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.83.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.84.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.84.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.84.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.85.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.85.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.85.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.86.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.86.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.86.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.87.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.87.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.87.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.88.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.88.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.88.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.89.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.89.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.89.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.9.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.9.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.9.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.90.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.90.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.90.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.91.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.91.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.91.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.92.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.92.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.92.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.93.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.93.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.93.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.94.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.94.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.94.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.95.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.95.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.95.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.96.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.96.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.96.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.97.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.97.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.97.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.98.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.98.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.98.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.99.w1.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.99.w2.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.99.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00008-of-00020.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.28.self_attn.k_norm.weight": "model-00008-of-00020.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.28.self_attn.q_norm.weight": "model-00008-of-00020.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.10.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.10.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.10.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.100.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.100.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.100.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.101.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.101.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.101.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.102.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.102.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.102.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.103.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.103.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.103.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.104.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.104.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.104.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.105.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.105.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.105.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.106.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.106.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.106.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.107.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.107.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.107.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.108.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.108.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.108.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.109.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.109.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.109.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.11.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.11.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.11.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.110.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.110.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.110.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.111.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.111.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.111.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.112.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.112.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.112.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.113.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.113.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.113.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.114.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.114.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.114.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.115.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.115.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.115.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.12.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.12.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.12.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.13.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.13.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.13.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.14.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.14.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.14.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.15.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.15.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.15.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.16.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.16.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.16.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.17.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.17.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.17.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.18.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.18.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.18.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.19.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.19.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.19.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.20.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.20.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.20.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.21.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.21.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.21.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.22.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.22.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.22.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.23.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.23.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.23.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.24.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.24.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.24.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.25.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.25.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.25.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.26.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.26.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.26.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.27.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.27.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.27.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.28.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.28.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.28.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.29.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.29.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.29.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.30.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.30.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.30.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.31.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.31.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.31.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.32.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.32.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.32.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.33.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.33.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.33.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.34.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.34.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.34.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.35.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.35.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.35.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.36.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.36.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.36.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.37.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.37.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.37.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.38.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.38.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.38.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.39.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.39.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.39.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.40.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.40.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.40.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.41.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.41.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.41.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.42.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.42.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.42.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.43.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.43.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.43.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.44.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.44.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.44.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.45.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.45.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.45.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.46.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.46.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.46.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.47.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.47.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.47.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.48.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.48.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.48.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.49.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.49.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.49.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.50.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.50.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.50.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.51.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.51.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.51.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.52.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.52.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.52.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.53.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.53.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.53.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.54.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.54.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.54.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.55.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.55.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.55.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.56.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.56.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.56.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.57.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.57.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.57.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.58.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.58.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.58.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.59.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.59.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.59.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.60.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.60.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.60.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.61.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.61.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.61.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.62.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.62.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.62.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.63.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.63.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.63.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.64.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.64.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.64.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.65.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.65.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.65.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.66.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.66.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.66.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.67.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.67.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.67.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.68.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.68.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.68.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.69.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.69.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.69.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.70.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.70.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.70.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.71.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.71.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.71.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.72.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.72.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.72.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.73.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.73.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.73.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.74.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.74.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.74.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.75.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.75.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.75.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.76.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.76.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.76.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.77.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.77.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.77.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.78.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.78.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.78.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.79.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.79.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.79.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.8.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.8.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.8.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.80.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.80.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.80.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.81.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.81.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.81.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.82.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.82.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.82.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.83.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.83.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.83.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.84.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.84.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.84.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.85.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.85.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.85.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.86.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.86.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.86.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.87.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.87.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.87.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.88.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.88.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.88.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.89.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.89.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.89.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.9.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.9.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.9.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.90.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.90.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.90.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.91.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.91.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.91.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.92.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.92.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.92.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.93.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.93.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.93.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.94.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.94.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.94.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.95.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.95.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.95.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.96.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.96.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.96.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.97.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.97.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.97.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.98.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.98.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.98.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.99.w1.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.99.w2.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.99.w3.weight": "model-00008-of-00020.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00008-of-00020.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.29.self_attn.k_norm.weight": "model-00008-of-00020.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.29.self_attn.q_norm.weight": "model-00008-of-00020.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.10.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.10.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.10.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.100.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.100.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.100.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.101.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.101.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.101.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.102.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.102.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.102.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.103.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.103.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.103.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.104.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.104.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.104.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.105.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.105.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.105.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.106.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.106.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.106.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.107.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.107.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.107.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.108.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.108.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.108.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.109.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.109.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.109.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.11.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.11.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.11.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.110.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.110.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.110.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.111.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.111.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.111.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.112.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.112.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.112.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.113.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.113.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.113.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.114.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.114.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.114.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.115.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.115.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.115.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.12.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.12.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.12.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.13.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.13.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.13.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.14.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.14.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.14.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.15.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.15.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.15.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.16.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.16.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.16.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.17.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.17.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.17.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.18.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.18.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.18.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.19.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.19.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.19.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.20.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.20.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.20.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.21.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.21.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.21.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.22.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.22.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.22.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.23.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.23.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.23.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.24.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.24.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.24.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.25.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.25.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.25.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.26.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.26.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.26.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.27.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.27.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.27.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.28.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.28.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.28.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.29.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.29.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.29.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.30.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.30.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.30.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.31.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.31.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.31.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.32.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.32.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.32.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.33.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.33.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.33.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.34.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.34.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.34.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.35.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.35.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.35.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.36.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.36.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.36.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.37.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.37.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.37.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.38.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.38.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.38.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.39.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.39.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.39.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.40.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.40.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.40.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.41.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.41.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.41.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.42.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.42.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.42.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.43.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.43.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.43.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.44.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.44.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.44.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.45.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.45.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.45.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.46.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.46.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.46.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.47.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.47.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.47.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.48.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.48.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.48.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.49.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.49.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.49.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.50.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.50.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.50.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.51.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.51.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.51.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.52.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.52.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.52.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.53.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.53.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.53.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.54.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.54.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.54.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.55.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.55.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.55.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.56.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.56.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.56.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.57.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.57.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.57.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.58.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.58.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.58.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.59.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.59.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.59.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.60.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.60.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.60.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.61.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.61.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.61.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.62.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.62.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.62.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.63.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.63.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.63.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.64.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.64.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.64.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.65.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.65.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.65.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.66.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.66.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.66.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.67.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.67.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.67.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.68.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.68.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.68.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.69.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.69.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.69.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.70.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.70.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.70.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.71.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.71.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.71.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.72.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.72.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.72.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.73.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.73.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.73.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.74.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.74.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.74.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.75.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.75.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.75.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.76.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.76.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.76.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.77.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.77.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.77.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.78.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.78.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.78.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.79.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.79.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.79.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.8.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.8.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.8.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.80.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.80.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.80.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.81.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.81.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.81.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.82.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.82.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.82.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.83.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.83.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.83.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.84.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.84.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.84.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.85.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.85.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.85.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.86.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.86.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.86.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.87.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.87.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.87.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.88.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.88.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.88.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.89.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.89.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.89.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.9.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.9.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.9.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.90.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.90.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.90.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.91.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.91.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.91.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.92.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.92.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.92.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.93.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.93.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.93.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.94.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.94.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.94.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.95.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.95.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.95.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.96.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.96.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.96.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.97.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.97.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.97.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.98.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.98.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.98.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.99.w1.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.99.w2.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.99.w3.weight": "model-00008-of-00020.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00008-of-00020.safetensors", "model.layers.3.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.3.self_attn.k_norm.weight": "model-00008-of-00020.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.3.self_attn.q_norm.weight": "model-00008-of-00020.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.10.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.10.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.10.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.100.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.100.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.100.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.101.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.101.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.101.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.102.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.102.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.102.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.103.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.103.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.103.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.104.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.104.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.104.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.105.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.105.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.105.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.106.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.106.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.106.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.107.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.107.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.107.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.108.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.108.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.108.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.109.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.109.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.109.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.11.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.11.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.11.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.110.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.110.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.110.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.111.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.111.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.111.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.112.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.112.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.112.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.113.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.113.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.113.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.114.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.114.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.114.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.115.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.115.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.115.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.12.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.12.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.12.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.13.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.13.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.13.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.14.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.14.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.14.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.15.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.15.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.15.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.16.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.16.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.16.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.17.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.17.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.17.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.18.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.18.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.18.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.19.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.19.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.19.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.20.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.20.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.20.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.21.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.21.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.21.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.22.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.22.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.22.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.23.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.23.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.23.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.24.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.24.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.24.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.25.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.25.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.25.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.26.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.26.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.26.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.27.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.27.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.27.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.28.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.28.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.28.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.29.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.29.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.29.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.30.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.30.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.30.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.31.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.31.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.31.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.32.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.32.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.32.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.33.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.33.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.33.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.34.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.34.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.34.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.35.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.35.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.35.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.36.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.36.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.36.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.37.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.37.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.37.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.38.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.38.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.38.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.39.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.39.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.39.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.40.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.40.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.40.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.41.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.41.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.41.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.42.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.42.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.42.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.43.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.43.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.43.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.44.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.44.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.44.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.45.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.45.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.45.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.46.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.46.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.46.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.47.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.47.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.47.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.48.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.48.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.48.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.49.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.49.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.49.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.50.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.50.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.50.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.51.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.51.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.51.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.52.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.52.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.52.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.53.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.53.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.53.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.54.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.54.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.54.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.55.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.55.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.55.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.56.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.56.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.56.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.57.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.57.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.57.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.58.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.58.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.58.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.59.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.59.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.59.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.60.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.60.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.60.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.61.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.61.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.61.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.62.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.62.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.62.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.63.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.63.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.63.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.64.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.64.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.64.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.65.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.65.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.65.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.66.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.66.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.66.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.67.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.67.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.67.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.68.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.68.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.68.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.69.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.69.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.69.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.70.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.70.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.70.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.71.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.71.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.71.w3.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.72.w1.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.72.w2.weight": "model-00008-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.72.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.73.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.73.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.73.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.74.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.74.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.74.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.75.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.75.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.75.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.76.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.76.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.76.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.77.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.77.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.77.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.78.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.78.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.78.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.79.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.79.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.79.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.8.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.8.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.8.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.80.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.80.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.80.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.81.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.81.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.81.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.82.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.82.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.82.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.83.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.83.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.83.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.84.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.84.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.84.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.85.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.85.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.85.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.86.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.86.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.86.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.87.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.87.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.87.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.88.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.88.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.88.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.89.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.89.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.89.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.9.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.9.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.9.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.90.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.90.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.90.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.91.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.91.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.91.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.92.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.92.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.92.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.93.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.93.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.93.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.94.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.94.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.94.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.95.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.95.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.95.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.96.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.96.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.96.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.97.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.97.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.97.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.98.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.98.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.98.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.99.w1.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.99.w2.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.99.w3.weight": "model-00009-of-00020.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00009-of-00020.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.30.self_attn.k_norm.weight": "model-00009-of-00020.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.30.self_attn.q_norm.weight": "model-00009-of-00020.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.10.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.10.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.10.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.100.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.100.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.100.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.101.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.101.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.101.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.102.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.102.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.102.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.103.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.103.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.103.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.104.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.104.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.104.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.105.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.105.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.105.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.106.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.106.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.106.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.107.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.107.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.107.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.108.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.108.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.108.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.109.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.109.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.109.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.11.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.11.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.11.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.110.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.110.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.110.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.111.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.111.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.111.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.112.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.112.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.112.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.113.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.113.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.113.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.114.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.114.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.114.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.115.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.115.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.115.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.12.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.12.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.12.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.13.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.13.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.13.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.14.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.14.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.14.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.15.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.15.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.15.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.16.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.16.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.16.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.17.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.17.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.17.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.18.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.18.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.18.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.19.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.19.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.19.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.20.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.20.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.20.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.21.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.21.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.21.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.22.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.22.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.22.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.23.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.23.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.23.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.24.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.24.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.24.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.25.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.25.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.25.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.26.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.26.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.26.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.27.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.27.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.27.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.28.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.28.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.28.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.29.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.29.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.29.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.30.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.30.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.30.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.31.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.31.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.31.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.32.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.32.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.32.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.33.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.33.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.33.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.34.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.34.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.34.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.35.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.35.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.35.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.36.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.36.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.36.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.37.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.37.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.37.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.38.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.38.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.38.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.39.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.39.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.39.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.40.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.40.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.40.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.41.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.41.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.41.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.42.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.42.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.42.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.43.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.43.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.43.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.44.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.44.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.44.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.45.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.45.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.45.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.46.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.46.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.46.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.47.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.47.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.47.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.48.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.48.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.48.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.49.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.49.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.49.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.50.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.50.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.50.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.51.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.51.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.51.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.52.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.52.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.52.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.53.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.53.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.53.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.54.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.54.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.54.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.55.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.55.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.55.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.56.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.56.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.56.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.57.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.57.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.57.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.58.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.58.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.58.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.59.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.59.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.59.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.60.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.60.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.60.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.61.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.61.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.61.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.62.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.62.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.62.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.63.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.63.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.63.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.64.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.64.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.64.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.65.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.65.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.65.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.66.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.66.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.66.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.67.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.67.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.67.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.68.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.68.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.68.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.69.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.69.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.69.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.70.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.70.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.70.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.71.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.71.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.71.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.72.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.72.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.72.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.73.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.73.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.73.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.74.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.74.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.74.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.75.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.75.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.75.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.76.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.76.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.76.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.77.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.77.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.77.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.78.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.78.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.78.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.79.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.79.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.79.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.8.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.8.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.8.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.80.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.80.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.80.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.81.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.81.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.81.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.82.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.82.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.82.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.83.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.83.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.83.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.84.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.84.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.84.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.85.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.85.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.85.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.86.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.86.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.86.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.87.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.87.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.87.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.88.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.88.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.88.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.89.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.89.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.89.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.9.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.9.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.9.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.90.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.90.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.90.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.91.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.91.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.91.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.92.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.92.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.92.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.93.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.93.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.93.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.94.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.94.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.94.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.95.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.95.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.95.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.96.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.96.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.96.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.97.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.97.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.97.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.98.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.98.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.98.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.99.w1.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.99.w2.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.99.w3.weight": "model-00009-of-00020.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00009-of-00020.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.31.self_attn.k_norm.weight": "model-00009-of-00020.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.31.self_attn.q_norm.weight": "model-00009-of-00020.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.10.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.10.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.10.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.100.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.100.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.100.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.101.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.101.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.101.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.102.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.102.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.102.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.103.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.103.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.103.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.104.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.104.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.104.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.105.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.105.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.105.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.106.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.106.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.106.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.107.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.107.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.107.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.108.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.108.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.108.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.109.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.109.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.109.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.11.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.11.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.11.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.110.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.110.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.110.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.111.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.111.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.111.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.112.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.112.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.112.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.113.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.113.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.113.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.114.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.114.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.114.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.115.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.115.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.115.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.12.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.12.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.12.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.13.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.13.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.13.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.14.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.14.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.14.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.15.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.15.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.15.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.16.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.16.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.16.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.17.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.17.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.17.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.18.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.18.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.18.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.19.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.19.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.19.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.20.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.20.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.20.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.21.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.21.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.21.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.22.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.22.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.22.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.23.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.23.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.23.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.24.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.24.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.24.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.25.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.25.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.25.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.26.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.26.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.26.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.27.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.27.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.27.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.28.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.28.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.28.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.29.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.29.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.29.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.30.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.30.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.30.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.31.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.31.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.31.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.32.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.32.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.32.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.33.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.33.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.33.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.34.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.34.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.34.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.35.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.35.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.35.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.36.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.36.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.36.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.37.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.37.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.37.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.38.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.38.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.38.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.39.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.39.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.39.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.40.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.40.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.40.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.41.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.41.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.41.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.42.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.42.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.42.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.43.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.43.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.43.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.44.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.44.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.44.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.45.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.45.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.45.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.46.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.46.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.46.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.47.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.47.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.47.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.48.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.48.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.48.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.49.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.49.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.49.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.50.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.50.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.50.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.51.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.51.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.51.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.52.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.52.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.52.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.53.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.53.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.53.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.54.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.54.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.54.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.55.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.55.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.55.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.56.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.56.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.56.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.57.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.57.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.57.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.58.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.58.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.58.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.59.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.59.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.59.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.60.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.60.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.60.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.61.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.61.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.61.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.62.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.62.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.62.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.63.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.63.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.63.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.64.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.64.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.64.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.65.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.65.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.65.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.66.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.66.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.66.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.67.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.67.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.67.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.68.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.68.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.68.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.69.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.69.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.69.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.70.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.70.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.70.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.71.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.71.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.71.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.72.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.72.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.72.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.73.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.73.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.73.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.74.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.74.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.74.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.75.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.75.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.75.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.76.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.76.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.76.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.77.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.77.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.77.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.78.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.78.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.78.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.79.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.79.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.79.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.8.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.8.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.8.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.80.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.80.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.80.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.81.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.81.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.81.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.82.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.82.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.82.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.83.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.83.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.83.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.84.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.84.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.84.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.85.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.85.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.85.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.86.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.86.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.86.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.87.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.87.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.87.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.88.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.88.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.88.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.89.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.89.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.89.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.9.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.9.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.9.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.90.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.90.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.90.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.91.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.91.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.91.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.92.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.92.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.92.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.93.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.93.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.93.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.94.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.94.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.94.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.95.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.95.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.95.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.96.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.96.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.96.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.97.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.97.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.97.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.98.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.98.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.98.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.99.w1.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.99.w2.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.99.w3.weight": "model-00009-of-00020.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00009-of-00020.safetensors", "model.layers.32.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.32.self_attn.k_norm.weight": "model-00009-of-00020.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.32.self_attn.q_norm.weight": "model-00009-of-00020.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.10.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.10.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.10.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.100.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.100.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.100.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.101.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.101.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.101.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.102.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.102.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.102.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.103.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.103.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.103.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.104.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.104.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.104.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.105.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.105.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.105.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.106.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.106.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.106.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.107.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.107.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.107.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.108.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.108.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.108.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.109.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.109.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.109.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.11.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.11.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.11.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.110.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.110.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.110.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.111.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.111.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.111.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.112.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.112.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.112.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.113.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.113.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.113.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.114.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.114.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.114.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.115.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.115.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.115.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.12.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.12.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.12.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.13.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.13.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.13.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.14.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.14.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.14.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.15.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.15.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.15.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.16.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.16.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.16.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.17.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.17.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.17.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.18.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.18.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.18.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.19.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.19.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.19.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.20.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.20.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.20.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.21.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.21.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.21.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.22.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.22.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.22.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.23.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.23.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.23.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.24.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.24.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.24.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.25.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.25.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.25.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.26.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.26.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.26.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.27.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.27.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.27.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.28.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.28.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.28.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.29.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.29.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.29.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.30.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.30.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.30.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.31.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.31.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.31.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.32.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.32.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.32.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.33.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.33.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.33.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.34.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.34.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.34.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.35.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.35.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.35.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.36.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.36.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.36.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.37.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.37.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.37.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.38.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.38.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.38.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.39.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.39.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.39.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.40.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.40.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.40.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.41.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.41.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.41.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.42.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.42.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.42.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.43.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.43.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.43.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.44.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.44.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.44.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.45.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.45.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.45.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.46.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.46.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.46.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.47.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.47.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.47.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.48.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.48.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.48.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.49.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.49.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.49.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.50.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.50.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.50.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.51.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.51.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.51.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.52.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.52.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.52.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.53.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.53.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.53.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.54.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.54.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.54.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.55.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.55.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.55.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.56.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.56.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.56.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.57.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.57.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.57.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.58.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.58.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.58.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.59.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.59.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.59.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.60.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.60.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.60.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.61.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.61.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.61.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.62.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.62.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.62.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.63.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.63.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.63.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.64.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.64.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.64.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.65.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.65.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.65.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.66.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.66.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.66.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.67.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.67.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.67.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.68.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.68.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.68.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.69.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.69.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.69.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.70.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.70.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.70.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.71.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.71.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.71.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.72.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.72.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.72.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.73.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.73.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.73.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.74.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.74.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.74.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.75.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.75.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.75.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.76.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.76.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.76.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.77.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.77.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.77.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.78.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.78.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.78.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.79.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.79.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.79.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.8.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.8.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.8.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.80.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.80.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.80.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.81.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.81.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.81.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.82.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.82.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.82.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.83.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.83.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.83.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.84.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.84.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.84.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.85.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.85.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.85.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.86.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.86.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.86.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.87.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.87.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.87.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.88.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.88.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.88.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.89.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.89.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.89.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.9.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.9.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.9.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.90.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.90.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.90.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.91.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.91.w2.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.91.w3.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.92.w1.weight": "model-00009-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.92.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.92.w3.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.93.w1.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.93.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.93.w3.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.94.w1.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.94.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.94.w3.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.95.w1.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.95.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.95.w3.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.96.w1.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.96.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.96.w3.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.97.w1.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.97.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.97.w3.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.98.w1.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.98.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.98.w3.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.99.w1.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.99.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.99.w3.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00010-of-00020.safetensors", "model.layers.33.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.33.self_attn.k_norm.weight": "model-00010-of-00020.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.33.self_attn.q_norm.weight": "model-00010-of-00020.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.10.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.10.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.10.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.100.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.100.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.100.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.101.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.101.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.101.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.102.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.102.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.102.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.103.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.103.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.103.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.104.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.104.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.104.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.105.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.105.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.105.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.106.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.106.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.106.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.107.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.107.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.107.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.108.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.108.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.108.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.109.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.109.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.109.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.11.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.11.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.11.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.110.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.110.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.110.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.111.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.111.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.111.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.112.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.112.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.112.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.113.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.113.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.113.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.114.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.114.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.114.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.115.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.115.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.115.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.12.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.12.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.12.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.13.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.13.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.13.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.14.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.14.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.14.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.15.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.15.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.15.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.16.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.16.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.16.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.17.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.17.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.17.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.18.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.18.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.18.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.19.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.19.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.19.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.20.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.20.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.20.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.21.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.21.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.21.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.22.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.22.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.22.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.23.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.23.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.23.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.24.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.24.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.24.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.25.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.25.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.25.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.26.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.26.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.26.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.27.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.27.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.27.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.28.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.28.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.28.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.29.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.29.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.29.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.30.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.30.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.30.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.31.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.31.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.31.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.32.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.32.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.32.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.33.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.33.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.33.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.34.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.34.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.34.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.35.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.35.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.35.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.36.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.36.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.36.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.37.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.37.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.37.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.38.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.38.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.38.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.39.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.39.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.39.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.40.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.40.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.40.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.41.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.41.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.41.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.42.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.42.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.42.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.43.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.43.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.43.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.44.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.44.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.44.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.45.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.45.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.45.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.46.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.46.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.46.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.47.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.47.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.47.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.48.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.48.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.48.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.49.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.49.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.49.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.50.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.50.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.50.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.51.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.51.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.51.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.52.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.52.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.52.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.53.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.53.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.53.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.54.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.54.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.54.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.55.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.55.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.55.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.56.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.56.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.56.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.57.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.57.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.57.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.58.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.58.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.58.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.59.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.59.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.59.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.60.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.60.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.60.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.61.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.61.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.61.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.62.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.62.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.62.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.63.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.63.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.63.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.64.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.64.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.64.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.65.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.65.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.65.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.66.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.66.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.66.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.67.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.67.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.67.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.68.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.68.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.68.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.69.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.69.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.69.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.70.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.70.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.70.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.71.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.71.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.71.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.72.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.72.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.72.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.73.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.73.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.73.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.74.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.74.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.74.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.75.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.75.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.75.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.76.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.76.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.76.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.77.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.77.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.77.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.78.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.78.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.78.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.79.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.79.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.79.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.8.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.8.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.8.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.80.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.80.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.80.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.81.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.81.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.81.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.82.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.82.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.82.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.83.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.83.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.83.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.84.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.84.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.84.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.85.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.85.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.85.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.86.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.86.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.86.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.87.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.87.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.87.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.88.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.88.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.88.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.89.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.89.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.89.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.9.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.9.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.9.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.90.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.90.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.90.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.91.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.91.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.91.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.92.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.92.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.92.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.93.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.93.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.93.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.94.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.94.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.94.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.95.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.95.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.95.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.96.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.96.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.96.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.97.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.97.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.97.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.98.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.98.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.98.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.99.w1.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.99.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.99.w3.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00010-of-00020.safetensors", "model.layers.34.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.34.self_attn.k_norm.weight": "model-00010-of-00020.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.34.self_attn.q_norm.weight": "model-00010-of-00020.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.10.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.10.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.10.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.100.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.100.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.100.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.101.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.101.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.101.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.102.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.102.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.102.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.103.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.103.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.103.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.104.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.104.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.104.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.105.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.105.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.105.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.106.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.106.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.106.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.107.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.107.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.107.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.108.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.108.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.108.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.109.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.109.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.109.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.11.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.11.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.11.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.110.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.110.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.110.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.111.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.111.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.111.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.112.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.112.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.112.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.113.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.113.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.113.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.114.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.114.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.114.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.115.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.115.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.115.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.12.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.12.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.12.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.13.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.13.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.13.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.14.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.14.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.14.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.15.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.15.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.15.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.16.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.16.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.16.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.17.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.17.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.17.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.18.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.18.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.18.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.19.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.19.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.19.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.20.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.20.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.20.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.21.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.21.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.21.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.22.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.22.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.22.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.23.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.23.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.23.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.24.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.24.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.24.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.25.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.25.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.25.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.26.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.26.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.26.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.27.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.27.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.27.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.28.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.28.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.28.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.29.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.29.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.29.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.30.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.30.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.30.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.31.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.31.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.31.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.32.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.32.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.32.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.33.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.33.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.33.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.34.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.34.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.34.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.35.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.35.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.35.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.36.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.36.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.36.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.37.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.37.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.37.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.38.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.38.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.38.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.39.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.39.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.39.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.40.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.40.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.40.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.41.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.41.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.41.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.42.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.42.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.42.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.43.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.43.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.43.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.44.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.44.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.44.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.45.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.45.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.45.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.46.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.46.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.46.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.47.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.47.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.47.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.48.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.48.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.48.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.49.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.49.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.49.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.50.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.50.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.50.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.51.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.51.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.51.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.52.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.52.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.52.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.53.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.53.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.53.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.54.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.54.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.54.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.55.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.55.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.55.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.56.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.56.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.56.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.57.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.57.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.57.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.58.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.58.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.58.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.59.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.59.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.59.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.60.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.60.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.60.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.61.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.61.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.61.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.62.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.62.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.62.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.63.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.63.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.63.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.64.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.64.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.64.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.65.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.65.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.65.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.66.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.66.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.66.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.67.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.67.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.67.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.68.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.68.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.68.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.69.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.69.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.69.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.70.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.70.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.70.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.71.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.71.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.71.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.72.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.72.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.72.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.73.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.73.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.73.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.74.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.74.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.74.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.75.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.75.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.75.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.76.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.76.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.76.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.77.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.77.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.77.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.78.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.78.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.78.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.79.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.79.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.79.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.8.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.8.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.8.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.80.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.80.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.80.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.81.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.81.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.81.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.82.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.82.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.82.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.83.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.83.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.83.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.84.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.84.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.84.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.85.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.85.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.85.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.86.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.86.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.86.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.87.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.87.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.87.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.88.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.88.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.88.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.89.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.89.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.89.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.9.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.9.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.9.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.90.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.90.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.90.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.91.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.91.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.91.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.92.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.92.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.92.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.93.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.93.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.93.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.94.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.94.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.94.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.95.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.95.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.95.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.96.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.96.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.96.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.97.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.97.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.97.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.98.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.98.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.98.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.99.w1.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.99.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.99.w3.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00010-of-00020.safetensors", "model.layers.35.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.35.self_attn.k_norm.weight": "model-00010-of-00020.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.35.self_attn.q_norm.weight": "model-00010-of-00020.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.10.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.10.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.10.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.100.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.100.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.100.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.101.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.101.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.101.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.102.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.102.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.102.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.103.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.103.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.103.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.104.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.104.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.104.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.105.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.105.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.105.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.106.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.106.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.106.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.107.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.107.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.107.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.108.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.108.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.108.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.109.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.109.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.109.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.11.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.11.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.11.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.110.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.110.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.110.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.111.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.111.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.111.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.112.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.112.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.112.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.113.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.113.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.113.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.114.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.114.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.114.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.115.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.115.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.115.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.12.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.12.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.12.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.13.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.13.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.13.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.14.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.14.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.14.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.15.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.15.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.15.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.16.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.16.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.16.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.17.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.17.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.17.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.18.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.18.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.18.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.19.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.19.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.19.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.20.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.20.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.20.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.21.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.21.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.21.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.22.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.22.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.22.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.23.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.23.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.23.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.24.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.24.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.24.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.25.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.25.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.25.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.26.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.26.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.26.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.27.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.27.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.27.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.28.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.28.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.28.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.29.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.29.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.29.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.30.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.30.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.30.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.31.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.31.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.31.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.32.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.32.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.32.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.33.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.33.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.33.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.34.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.34.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.34.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.35.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.35.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.35.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.36.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.36.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.36.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.37.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.37.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.37.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.38.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.38.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.38.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.39.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.39.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.39.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.40.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.40.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.40.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.41.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.41.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.41.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.42.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.42.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.42.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.43.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.43.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.43.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.44.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.44.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.44.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.45.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.45.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.45.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.46.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.46.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.46.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.47.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.47.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.47.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.48.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.48.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.48.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.49.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.49.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.49.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.50.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.50.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.50.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.51.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.51.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.51.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.52.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.52.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.52.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.53.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.53.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.53.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.54.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.54.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.54.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.55.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.55.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.55.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.56.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.56.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.56.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.57.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.57.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.57.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.58.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.58.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.58.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.59.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.59.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.59.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.60.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.60.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.60.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.61.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.61.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.61.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.62.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.62.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.62.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.63.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.63.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.63.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.64.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.64.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.64.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.65.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.65.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.65.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.66.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.66.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.66.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.67.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.67.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.67.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.68.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.68.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.68.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.69.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.69.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.69.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.70.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.70.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.70.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.71.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.71.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.71.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.72.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.72.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.72.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.73.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.73.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.73.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.74.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.74.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.74.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.75.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.75.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.75.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.76.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.76.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.76.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.77.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.77.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.77.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.78.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.78.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.78.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.79.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.79.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.79.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.8.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.8.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.8.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.80.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.80.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.80.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.81.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.81.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.81.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.82.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.82.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.82.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.83.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.83.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.83.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.84.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.84.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.84.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.85.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.85.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.85.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.86.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.86.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.86.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.87.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.87.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.87.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.88.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.88.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.88.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.89.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.89.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.89.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.9.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.9.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.9.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.90.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.90.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.90.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.91.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.91.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.91.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.92.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.92.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.92.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.93.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.93.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.93.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.94.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.94.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.94.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.95.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.95.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.95.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.96.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.96.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.96.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.97.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.97.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.97.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.98.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.98.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.98.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.99.w1.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.99.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.99.w3.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00010-of-00020.safetensors", "model.layers.36.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.36.self_attn.k_norm.weight": "model-00010-of-00020.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.36.self_attn.q_norm.weight": "model-00010-of-00020.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.10.w1.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.10.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.10.w3.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.100.w1.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.100.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.100.w3.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.101.w1.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.101.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.101.w3.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.102.w1.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.102.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.102.w3.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.103.w1.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.103.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.103.w3.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.104.w1.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.104.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.104.w3.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.105.w1.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.105.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.105.w3.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.106.w1.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.106.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.106.w3.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.107.w1.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.107.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.107.w3.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.108.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.108.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.108.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.109.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.109.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.109.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.11.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.11.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.11.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.110.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.110.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.110.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.111.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.111.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.111.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.112.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.112.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.112.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.113.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.113.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.113.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.114.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.114.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.114.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.115.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.115.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.115.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.12.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.12.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.12.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.13.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.13.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.13.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.14.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.14.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.14.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.15.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.15.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.15.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.16.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.16.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.16.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.17.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.17.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.17.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.18.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.18.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.18.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.19.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.19.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.19.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.20.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.20.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.20.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.21.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.21.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.21.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.22.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.22.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.22.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.23.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.23.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.23.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.24.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.24.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.24.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.25.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.25.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.25.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.26.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.26.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.26.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.27.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.27.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.27.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.28.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.28.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.28.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.29.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.29.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.29.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.30.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.30.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.30.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.31.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.31.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.31.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.32.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.32.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.32.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.33.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.33.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.33.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.34.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.34.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.34.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.35.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.35.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.35.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.36.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.36.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.36.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.37.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.37.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.37.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.38.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.38.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.38.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.39.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.39.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.39.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.40.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.40.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.40.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.41.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.41.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.41.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.42.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.42.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.42.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.43.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.43.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.43.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.44.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.44.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.44.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.45.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.45.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.45.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.46.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.46.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.46.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.47.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.47.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.47.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.48.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.48.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.48.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.49.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.49.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.49.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.50.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.50.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.50.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.51.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.51.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.51.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.52.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.52.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.52.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.53.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.53.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.53.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.54.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.54.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.54.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.55.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.55.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.55.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.56.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.56.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.56.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.57.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.57.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.57.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.58.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.58.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.58.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.59.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.59.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.59.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.60.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.60.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.60.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.61.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.61.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.61.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.62.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.62.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.62.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.63.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.63.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.63.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.64.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.64.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.64.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.65.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.65.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.65.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.66.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.66.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.66.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.67.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.67.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.67.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.68.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.68.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.68.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.69.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.69.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.69.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.70.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.70.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.70.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.71.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.71.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.71.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.72.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.72.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.72.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.73.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.73.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.73.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.74.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.74.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.74.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.75.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.75.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.75.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.76.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.76.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.76.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.77.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.77.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.77.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.78.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.78.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.78.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.79.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.79.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.79.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.8.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.8.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.8.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.80.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.80.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.80.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.81.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.81.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.81.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.82.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.82.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.82.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.83.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.83.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.83.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.84.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.84.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.84.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.85.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.85.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.85.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.86.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.86.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.86.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.87.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.87.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.87.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.88.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.88.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.88.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.89.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.89.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.89.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.9.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.9.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.9.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.90.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.90.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.90.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.91.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.91.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.91.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.92.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.92.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.92.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.93.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.93.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.93.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.94.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.94.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.94.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.95.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.95.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.95.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.96.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.96.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.96.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.97.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.97.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.97.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.98.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.98.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.98.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.99.w1.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.99.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.99.w3.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00011-of-00020.safetensors", "model.layers.37.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.37.self_attn.k_norm.weight": "model-00011-of-00020.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.37.self_attn.q_norm.weight": "model-00011-of-00020.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.10.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.10.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.10.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.100.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.100.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.100.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.101.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.101.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.101.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.102.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.102.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.102.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.103.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.103.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.103.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.104.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.104.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.104.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.105.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.105.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.105.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.106.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.106.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.106.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.107.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.107.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.107.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.108.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.108.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.108.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.109.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.109.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.109.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.11.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.11.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.11.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.110.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.110.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.110.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.111.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.111.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.111.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.112.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.112.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.112.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.113.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.113.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.113.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.114.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.114.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.114.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.115.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.115.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.115.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.12.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.12.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.12.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.13.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.13.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.13.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.14.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.14.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.14.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.15.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.15.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.15.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.16.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.16.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.16.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.17.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.17.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.17.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.18.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.18.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.18.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.19.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.19.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.19.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.20.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.20.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.20.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.21.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.21.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.21.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.22.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.22.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.22.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.23.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.23.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.23.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.24.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.24.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.24.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.25.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.25.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.25.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.26.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.26.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.26.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.27.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.27.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.27.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.28.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.28.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.28.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.29.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.29.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.29.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.30.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.30.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.30.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.31.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.31.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.31.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.32.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.32.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.32.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.33.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.33.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.33.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.34.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.34.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.34.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.35.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.35.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.35.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.36.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.36.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.36.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.37.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.37.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.37.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.38.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.38.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.38.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.39.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.39.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.39.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.40.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.40.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.40.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.41.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.41.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.41.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.42.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.42.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.42.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.43.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.43.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.43.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.44.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.44.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.44.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.45.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.45.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.45.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.46.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.46.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.46.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.47.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.47.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.47.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.48.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.48.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.48.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.49.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.49.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.49.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.50.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.50.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.50.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.51.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.51.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.51.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.52.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.52.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.52.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.53.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.53.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.53.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.54.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.54.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.54.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.55.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.55.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.55.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.56.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.56.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.56.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.57.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.57.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.57.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.58.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.58.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.58.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.59.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.59.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.59.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.60.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.60.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.60.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.61.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.61.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.61.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.62.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.62.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.62.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.63.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.63.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.63.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.64.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.64.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.64.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.65.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.65.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.65.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.66.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.66.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.66.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.67.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.67.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.67.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.68.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.68.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.68.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.69.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.69.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.69.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.70.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.70.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.70.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.71.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.71.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.71.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.72.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.72.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.72.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.73.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.73.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.73.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.74.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.74.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.74.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.75.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.75.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.75.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.76.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.76.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.76.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.77.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.77.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.77.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.78.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.78.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.78.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.79.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.79.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.79.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.8.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.8.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.8.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.80.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.80.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.80.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.81.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.81.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.81.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.82.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.82.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.82.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.83.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.83.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.83.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.84.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.84.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.84.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.85.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.85.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.85.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.86.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.86.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.86.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.87.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.87.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.87.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.88.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.88.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.88.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.89.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.89.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.89.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.9.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.9.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.9.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.90.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.90.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.90.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.91.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.91.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.91.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.92.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.92.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.92.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.93.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.93.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.93.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.94.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.94.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.94.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.95.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.95.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.95.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.96.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.96.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.96.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.97.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.97.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.97.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.98.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.98.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.98.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.99.w1.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.99.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.99.w3.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00011-of-00020.safetensors", "model.layers.38.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.38.self_attn.k_norm.weight": "model-00011-of-00020.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.38.self_attn.q_norm.weight": "model-00011-of-00020.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.10.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.10.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.10.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.100.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.100.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.100.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.101.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.101.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.101.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.102.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.102.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.102.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.103.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.103.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.103.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.104.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.104.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.104.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.105.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.105.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.105.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.106.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.106.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.106.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.107.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.107.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.107.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.108.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.108.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.108.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.109.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.109.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.109.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.11.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.11.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.11.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.110.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.110.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.110.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.111.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.111.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.111.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.112.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.112.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.112.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.113.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.113.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.113.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.114.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.114.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.114.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.115.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.115.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.115.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.12.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.12.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.12.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.13.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.13.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.13.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.14.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.14.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.14.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.15.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.15.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.15.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.16.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.16.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.16.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.17.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.17.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.17.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.18.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.18.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.18.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.19.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.19.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.19.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.20.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.20.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.20.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.21.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.21.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.21.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.22.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.22.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.22.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.23.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.23.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.23.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.24.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.24.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.24.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.25.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.25.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.25.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.26.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.26.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.26.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.27.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.27.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.27.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.28.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.28.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.28.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.29.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.29.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.29.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.30.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.30.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.30.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.31.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.31.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.31.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.32.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.32.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.32.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.33.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.33.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.33.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.34.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.34.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.34.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.35.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.35.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.35.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.36.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.36.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.36.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.37.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.37.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.37.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.38.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.38.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.38.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.39.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.39.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.39.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.40.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.40.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.40.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.41.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.41.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.41.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.42.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.42.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.42.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.43.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.43.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.43.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.44.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.44.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.44.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.45.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.45.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.45.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.46.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.46.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.46.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.47.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.47.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.47.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.48.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.48.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.48.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.49.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.49.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.49.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.50.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.50.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.50.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.51.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.51.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.51.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.52.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.52.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.52.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.53.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.53.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.53.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.54.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.54.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.54.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.55.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.55.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.55.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.56.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.56.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.56.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.57.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.57.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.57.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.58.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.58.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.58.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.59.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.59.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.59.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.60.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.60.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.60.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.61.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.61.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.61.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.62.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.62.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.62.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.63.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.63.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.63.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.64.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.64.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.64.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.65.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.65.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.65.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.66.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.66.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.66.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.67.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.67.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.67.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.68.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.68.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.68.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.69.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.69.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.69.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.70.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.70.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.70.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.71.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.71.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.71.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.72.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.72.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.72.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.73.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.73.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.73.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.74.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.74.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.74.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.75.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.75.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.75.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.76.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.76.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.76.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.77.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.77.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.77.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.78.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.78.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.78.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.79.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.79.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.79.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.8.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.8.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.8.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.80.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.80.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.80.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.81.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.81.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.81.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.82.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.82.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.82.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.83.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.83.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.83.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.84.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.84.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.84.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.85.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.85.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.85.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.86.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.86.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.86.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.87.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.87.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.87.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.88.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.88.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.88.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.89.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.89.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.89.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.9.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.9.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.9.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.90.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.90.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.90.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.91.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.91.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.91.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.92.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.92.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.92.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.93.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.93.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.93.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.94.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.94.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.94.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.95.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.95.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.95.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.96.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.96.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.96.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.97.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.97.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.97.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.98.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.98.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.98.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.99.w1.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.99.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.99.w3.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00011-of-00020.safetensors", "model.layers.39.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.39.self_attn.k_norm.weight": "model-00011-of-00020.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.39.self_attn.q_norm.weight": "model-00011-of-00020.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.10.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.10.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.10.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.100.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.100.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.100.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.101.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.101.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.101.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.102.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.102.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.102.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.103.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.103.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.103.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.104.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.104.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.104.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.105.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.105.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.105.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.106.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.106.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.106.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.107.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.107.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.107.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.108.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.108.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.108.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.109.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.109.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.109.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.11.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.11.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.11.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.110.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.110.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.110.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.111.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.111.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.111.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.112.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.112.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.112.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.113.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.113.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.113.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.114.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.114.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.114.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.115.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.115.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.115.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.12.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.12.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.12.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.13.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.13.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.13.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.14.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.14.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.14.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.15.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.15.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.15.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.16.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.16.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.16.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.17.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.17.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.17.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.18.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.18.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.18.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.19.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.19.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.19.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.20.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.20.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.20.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.21.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.21.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.21.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.22.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.22.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.22.w3.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.23.w1.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.23.w2.weight": "model-00011-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.23.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.24.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.24.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.24.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.25.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.25.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.25.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.26.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.26.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.26.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.27.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.27.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.27.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.28.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.28.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.28.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.29.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.29.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.29.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.30.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.30.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.30.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.31.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.31.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.31.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.32.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.32.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.32.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.33.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.33.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.33.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.34.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.34.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.34.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.35.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.35.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.35.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.36.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.36.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.36.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.37.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.37.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.37.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.38.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.38.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.38.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.39.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.39.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.39.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.40.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.40.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.40.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.41.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.41.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.41.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.42.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.42.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.42.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.43.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.43.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.43.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.44.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.44.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.44.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.45.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.45.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.45.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.46.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.46.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.46.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.47.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.47.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.47.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.48.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.48.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.48.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.49.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.49.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.49.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.50.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.50.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.50.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.51.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.51.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.51.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.52.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.52.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.52.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.53.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.53.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.53.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.54.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.54.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.54.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.55.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.55.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.55.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.56.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.56.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.56.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.57.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.57.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.57.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.58.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.58.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.58.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.59.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.59.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.59.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.60.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.60.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.60.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.61.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.61.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.61.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.62.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.62.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.62.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.63.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.63.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.63.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.64.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.64.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.64.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.65.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.65.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.65.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.66.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.66.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.66.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.67.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.67.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.67.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.68.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.68.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.68.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.69.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.69.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.69.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.70.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.70.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.70.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.71.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.71.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.71.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.72.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.72.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.72.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.73.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.73.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.73.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.74.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.74.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.74.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.75.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.75.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.75.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.76.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.76.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.76.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.77.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.77.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.77.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.78.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.78.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.78.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.79.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.79.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.79.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.8.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.8.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.8.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.80.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.80.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.80.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.81.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.81.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.81.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.82.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.82.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.82.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.83.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.83.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.83.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.84.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.84.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.84.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.85.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.85.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.85.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.86.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.86.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.86.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.87.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.87.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.87.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.88.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.88.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.88.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.89.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.89.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.89.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.9.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.9.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.9.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.90.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.90.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.90.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.91.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.91.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.91.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.92.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.92.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.92.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.93.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.93.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.93.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.94.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.94.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.94.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.95.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.95.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.95.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.96.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.96.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.96.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.97.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.97.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.97.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.98.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.98.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.98.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.99.w1.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.99.w2.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.99.w3.weight": "model-00012-of-00020.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00012-of-00020.safetensors", "model.layers.4.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.4.self_attn.k_norm.weight": "model-00012-of-00020.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.4.self_attn.q_norm.weight": "model-00012-of-00020.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.10.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.10.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.10.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.100.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.100.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.100.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.101.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.101.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.101.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.102.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.102.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.102.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.103.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.103.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.103.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.104.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.104.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.104.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.105.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.105.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.105.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.106.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.106.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.106.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.107.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.107.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.107.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.108.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.108.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.108.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.109.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.109.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.109.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.11.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.11.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.11.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.110.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.110.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.110.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.111.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.111.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.111.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.112.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.112.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.112.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.113.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.113.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.113.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.114.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.114.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.114.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.115.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.115.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.115.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.12.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.12.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.12.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.13.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.13.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.13.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.14.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.14.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.14.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.15.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.15.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.15.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.16.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.16.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.16.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.17.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.17.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.17.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.18.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.18.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.18.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.19.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.19.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.19.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.20.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.20.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.20.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.21.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.21.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.21.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.22.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.22.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.22.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.23.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.23.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.23.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.24.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.24.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.24.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.25.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.25.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.25.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.26.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.26.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.26.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.27.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.27.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.27.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.28.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.28.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.28.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.29.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.29.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.29.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.30.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.30.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.30.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.31.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.31.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.31.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.32.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.32.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.32.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.33.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.33.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.33.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.34.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.34.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.34.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.35.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.35.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.35.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.36.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.36.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.36.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.37.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.37.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.37.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.38.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.38.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.38.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.39.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.39.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.39.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.40.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.40.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.40.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.41.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.41.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.41.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.42.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.42.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.42.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.43.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.43.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.43.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.44.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.44.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.44.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.45.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.45.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.45.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.46.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.46.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.46.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.47.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.47.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.47.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.48.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.48.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.48.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.49.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.49.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.49.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.50.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.50.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.50.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.51.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.51.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.51.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.52.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.52.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.52.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.53.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.53.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.53.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.54.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.54.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.54.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.55.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.55.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.55.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.56.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.56.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.56.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.57.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.57.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.57.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.58.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.58.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.58.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.59.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.59.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.59.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.60.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.60.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.60.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.61.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.61.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.61.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.62.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.62.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.62.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.63.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.63.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.63.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.64.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.64.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.64.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.65.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.65.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.65.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.66.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.66.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.66.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.67.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.67.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.67.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.68.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.68.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.68.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.69.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.69.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.69.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.70.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.70.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.70.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.71.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.71.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.71.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.72.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.72.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.72.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.73.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.73.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.73.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.74.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.74.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.74.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.75.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.75.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.75.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.76.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.76.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.76.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.77.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.77.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.77.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.78.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.78.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.78.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.79.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.79.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.79.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.8.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.8.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.8.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.80.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.80.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.80.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.81.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.81.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.81.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.82.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.82.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.82.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.83.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.83.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.83.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.84.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.84.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.84.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.85.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.85.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.85.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.86.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.86.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.86.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.87.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.87.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.87.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.88.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.88.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.88.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.89.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.89.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.89.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.9.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.9.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.9.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.90.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.90.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.90.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.91.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.91.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.91.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.92.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.92.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.92.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.93.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.93.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.93.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.94.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.94.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.94.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.95.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.95.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.95.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.96.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.96.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.96.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.97.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.97.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.97.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.98.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.98.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.98.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.99.w1.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.99.w2.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.99.w3.weight": "model-00012-of-00020.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00012-of-00020.safetensors", "model.layers.40.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.40.self_attn.k_norm.weight": "model-00012-of-00020.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.40.self_attn.q_norm.weight": "model-00012-of-00020.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.10.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.10.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.10.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.100.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.100.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.100.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.101.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.101.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.101.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.102.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.102.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.102.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.103.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.103.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.103.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.104.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.104.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.104.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.105.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.105.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.105.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.106.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.106.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.106.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.107.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.107.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.107.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.108.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.108.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.108.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.109.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.109.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.109.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.11.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.11.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.11.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.110.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.110.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.110.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.111.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.111.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.111.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.112.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.112.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.112.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.113.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.113.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.113.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.114.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.114.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.114.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.115.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.115.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.115.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.12.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.12.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.12.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.13.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.13.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.13.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.14.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.14.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.14.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.15.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.15.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.15.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.16.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.16.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.16.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.17.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.17.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.17.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.18.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.18.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.18.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.19.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.19.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.19.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.20.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.20.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.20.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.21.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.21.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.21.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.22.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.22.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.22.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.23.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.23.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.23.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.24.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.24.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.24.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.25.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.25.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.25.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.26.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.26.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.26.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.27.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.27.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.27.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.28.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.28.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.28.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.29.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.29.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.29.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.30.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.30.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.30.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.31.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.31.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.31.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.32.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.32.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.32.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.33.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.33.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.33.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.34.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.34.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.34.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.35.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.35.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.35.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.36.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.36.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.36.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.37.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.37.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.37.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.38.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.38.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.38.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.39.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.39.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.39.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.40.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.40.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.40.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.41.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.41.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.41.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.42.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.42.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.42.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.43.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.43.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.43.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.44.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.44.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.44.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.45.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.45.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.45.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.46.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.46.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.46.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.47.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.47.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.47.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.48.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.48.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.48.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.49.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.49.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.49.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.50.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.50.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.50.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.51.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.51.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.51.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.52.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.52.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.52.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.53.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.53.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.53.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.54.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.54.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.54.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.55.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.55.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.55.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.56.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.56.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.56.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.57.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.57.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.57.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.58.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.58.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.58.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.59.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.59.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.59.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.60.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.60.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.60.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.61.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.61.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.61.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.62.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.62.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.62.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.63.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.63.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.63.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.64.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.64.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.64.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.65.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.65.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.65.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.66.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.66.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.66.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.67.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.67.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.67.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.68.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.68.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.68.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.69.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.69.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.69.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.70.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.70.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.70.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.71.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.71.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.71.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.72.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.72.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.72.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.73.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.73.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.73.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.74.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.74.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.74.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.75.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.75.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.75.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.76.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.76.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.76.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.77.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.77.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.77.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.78.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.78.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.78.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.79.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.79.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.79.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.8.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.8.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.8.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.80.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.80.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.80.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.81.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.81.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.81.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.82.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.82.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.82.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.83.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.83.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.83.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.84.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.84.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.84.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.85.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.85.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.85.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.86.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.86.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.86.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.87.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.87.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.87.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.88.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.88.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.88.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.89.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.89.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.89.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.9.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.9.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.9.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.90.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.90.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.90.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.91.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.91.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.91.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.92.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.92.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.92.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.93.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.93.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.93.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.94.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.94.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.94.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.95.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.95.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.95.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.96.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.96.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.96.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.97.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.97.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.97.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.98.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.98.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.98.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.99.w1.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.99.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.99.w3.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00012-of-00020.safetensors", "model.layers.41.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.41.self_attn.k_norm.weight": "model-00012-of-00020.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.41.self_attn.q_norm.weight": "model-00012-of-00020.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.10.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.10.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.10.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.100.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.100.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.100.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.101.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.101.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.101.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.102.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.102.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.102.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.103.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.103.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.103.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.104.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.104.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.104.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.105.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.105.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.105.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.106.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.106.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.106.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.107.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.107.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.107.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.108.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.108.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.108.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.109.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.109.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.109.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.11.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.11.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.11.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.110.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.110.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.110.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.111.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.111.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.111.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.112.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.112.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.112.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.113.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.113.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.113.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.114.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.114.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.114.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.115.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.115.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.115.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.12.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.12.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.12.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.13.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.13.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.13.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.14.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.14.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.14.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.15.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.15.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.15.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.16.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.16.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.16.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.17.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.17.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.17.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.18.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.18.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.18.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.19.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.19.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.19.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.20.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.20.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.20.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.21.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.21.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.21.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.22.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.22.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.22.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.23.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.23.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.23.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.24.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.24.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.24.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.25.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.25.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.25.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.26.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.26.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.26.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.27.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.27.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.27.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.28.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.28.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.28.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.29.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.29.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.29.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.30.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.30.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.30.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.31.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.31.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.31.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.32.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.32.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.32.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.33.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.33.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.33.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.34.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.34.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.34.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.35.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.35.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.35.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.36.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.36.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.36.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.37.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.37.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.37.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.38.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.38.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.38.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.39.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.39.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.39.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.40.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.40.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.40.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.41.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.41.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.41.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.42.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.42.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.42.w3.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.43.w1.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.43.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.43.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.44.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.44.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.44.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.45.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.45.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.45.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.46.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.46.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.46.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.47.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.47.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.47.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.48.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.48.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.48.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.49.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.49.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.49.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.50.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.50.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.50.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.51.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.51.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.51.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.52.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.52.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.52.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.53.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.53.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.53.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.54.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.54.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.54.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.55.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.55.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.55.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.56.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.56.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.56.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.57.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.57.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.57.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.58.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.58.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.58.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.59.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.59.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.59.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.60.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.60.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.60.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.61.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.61.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.61.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.62.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.62.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.62.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.63.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.63.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.63.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.64.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.64.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.64.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.65.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.65.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.65.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.66.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.66.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.66.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.67.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.67.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.67.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.68.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.68.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.68.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.69.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.69.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.69.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.70.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.70.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.70.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.71.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.71.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.71.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.72.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.72.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.72.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.73.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.73.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.73.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.74.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.74.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.74.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.75.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.75.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.75.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.76.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.76.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.76.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.77.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.77.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.77.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.78.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.78.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.78.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.79.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.79.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.79.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.8.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.8.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.8.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.80.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.80.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.80.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.81.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.81.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.81.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.82.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.82.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.82.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.83.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.83.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.83.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.84.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.84.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.84.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.85.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.85.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.85.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.86.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.86.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.86.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.87.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.87.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.87.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.88.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.88.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.88.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.89.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.89.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.89.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.9.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.9.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.9.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.90.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.90.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.90.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.91.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.91.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.91.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.92.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.92.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.92.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.93.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.93.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.93.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.94.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.94.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.94.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.95.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.95.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.95.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.96.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.96.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.96.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.97.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.97.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.97.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.98.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.98.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.98.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.99.w1.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.99.w2.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.99.w3.weight": "model-00013-of-00020.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00013-of-00020.safetensors", "model.layers.42.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.42.self_attn.k_norm.weight": "model-00013-of-00020.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.42.self_attn.q_norm.weight": "model-00013-of-00020.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.10.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.10.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.10.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.100.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.100.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.100.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.101.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.101.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.101.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.102.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.102.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.102.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.103.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.103.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.103.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.104.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.104.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.104.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.105.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.105.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.105.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.106.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.106.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.106.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.107.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.107.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.107.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.108.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.108.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.108.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.109.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.109.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.109.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.11.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.11.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.11.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.110.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.110.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.110.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.111.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.111.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.111.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.112.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.112.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.112.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.113.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.113.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.113.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.114.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.114.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.114.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.115.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.115.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.115.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.12.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.12.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.12.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.13.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.13.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.13.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.14.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.14.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.14.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.15.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.15.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.15.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.16.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.16.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.16.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.17.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.17.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.17.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.18.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.18.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.18.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.19.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.19.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.19.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.20.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.20.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.20.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.21.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.21.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.21.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.22.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.22.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.22.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.23.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.23.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.23.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.24.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.24.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.24.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.25.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.25.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.25.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.26.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.26.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.26.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.27.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.27.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.27.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.28.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.28.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.28.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.29.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.29.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.29.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.30.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.30.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.30.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.31.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.31.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.31.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.32.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.32.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.32.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.33.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.33.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.33.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.34.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.34.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.34.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.35.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.35.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.35.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.36.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.36.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.36.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.37.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.37.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.37.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.38.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.38.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.38.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.39.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.39.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.39.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.40.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.40.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.40.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.41.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.41.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.41.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.42.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.42.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.42.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.43.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.43.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.43.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.44.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.44.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.44.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.45.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.45.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.45.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.46.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.46.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.46.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.47.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.47.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.47.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.48.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.48.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.48.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.49.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.49.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.49.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.50.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.50.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.50.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.51.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.51.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.51.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.52.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.52.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.52.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.53.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.53.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.53.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.54.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.54.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.54.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.55.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.55.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.55.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.56.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.56.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.56.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.57.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.57.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.57.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.58.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.58.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.58.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.59.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.59.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.59.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.60.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.60.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.60.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.61.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.61.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.61.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.62.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.62.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.62.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.63.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.63.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.63.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.64.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.64.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.64.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.65.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.65.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.65.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.66.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.66.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.66.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.67.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.67.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.67.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.68.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.68.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.68.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.69.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.69.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.69.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.70.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.70.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.70.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.71.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.71.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.71.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.72.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.72.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.72.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.73.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.73.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.73.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.74.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.74.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.74.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.75.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.75.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.75.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.76.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.76.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.76.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.77.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.77.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.77.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.78.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.78.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.78.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.79.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.79.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.79.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.8.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.8.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.8.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.80.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.80.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.80.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.81.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.81.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.81.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.82.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.82.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.82.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.83.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.83.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.83.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.84.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.84.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.84.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.85.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.85.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.85.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.86.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.86.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.86.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.87.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.87.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.87.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.88.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.88.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.88.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.89.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.89.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.89.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.9.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.9.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.9.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.90.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.90.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.90.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.91.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.91.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.91.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.92.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.92.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.92.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.93.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.93.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.93.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.94.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.94.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.94.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.95.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.95.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.95.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.96.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.96.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.96.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.97.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.97.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.97.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.98.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.98.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.98.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.99.w1.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.99.w2.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.99.w3.weight": "model-00013-of-00020.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00013-of-00020.safetensors", "model.layers.43.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.43.self_attn.k_norm.weight": "model-00013-of-00020.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.43.self_attn.q_norm.weight": "model-00013-of-00020.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.10.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.10.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.10.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.100.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.100.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.100.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.101.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.101.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.101.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.102.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.102.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.102.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.103.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.103.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.103.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.104.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.104.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.104.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.105.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.105.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.105.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.106.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.106.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.106.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.107.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.107.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.107.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.108.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.108.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.108.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.109.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.109.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.109.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.11.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.11.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.11.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.110.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.110.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.110.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.111.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.111.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.111.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.112.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.112.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.112.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.113.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.113.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.113.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.114.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.114.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.114.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.115.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.115.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.115.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.12.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.12.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.12.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.13.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.13.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.13.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.14.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.14.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.14.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.15.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.15.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.15.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.16.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.16.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.16.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.17.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.17.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.17.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.18.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.18.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.18.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.19.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.19.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.19.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.20.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.20.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.20.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.21.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.21.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.21.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.22.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.22.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.22.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.23.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.23.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.23.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.24.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.24.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.24.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.25.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.25.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.25.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.26.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.26.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.26.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.27.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.27.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.27.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.28.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.28.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.28.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.29.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.29.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.29.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.30.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.30.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.30.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.31.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.31.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.31.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.32.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.32.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.32.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.33.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.33.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.33.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.34.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.34.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.34.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.35.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.35.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.35.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.36.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.36.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.36.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.37.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.37.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.37.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.38.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.38.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.38.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.39.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.39.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.39.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.40.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.40.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.40.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.41.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.41.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.41.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.42.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.42.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.42.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.43.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.43.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.43.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.44.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.44.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.44.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.45.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.45.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.45.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.46.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.46.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.46.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.47.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.47.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.47.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.48.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.48.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.48.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.49.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.49.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.49.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.50.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.50.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.50.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.51.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.51.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.51.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.52.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.52.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.52.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.53.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.53.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.53.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.54.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.54.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.54.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.55.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.55.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.55.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.56.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.56.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.56.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.57.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.57.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.57.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.58.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.58.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.58.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.59.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.59.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.59.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.60.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.60.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.60.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.61.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.61.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.61.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.62.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.62.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.62.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.63.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.63.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.63.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.64.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.64.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.64.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.65.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.65.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.65.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.66.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.66.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.66.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.67.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.67.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.67.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.68.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.68.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.68.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.69.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.69.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.69.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.70.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.70.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.70.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.71.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.71.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.71.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.72.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.72.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.72.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.73.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.73.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.73.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.74.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.74.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.74.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.75.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.75.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.75.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.76.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.76.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.76.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.77.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.77.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.77.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.78.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.78.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.78.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.79.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.79.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.79.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.8.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.8.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.8.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.80.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.80.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.80.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.81.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.81.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.81.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.82.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.82.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.82.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.83.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.83.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.83.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.84.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.84.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.84.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.85.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.85.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.85.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.86.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.86.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.86.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.87.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.87.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.87.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.88.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.88.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.88.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.89.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.89.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.89.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.9.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.9.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.9.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.90.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.90.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.90.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.91.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.91.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.91.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.92.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.92.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.92.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.93.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.93.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.93.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.94.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.94.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.94.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.95.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.95.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.95.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.96.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.96.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.96.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.97.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.97.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.97.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.98.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.98.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.98.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.99.w1.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.99.w2.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.99.w3.weight": "model-00013-of-00020.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00013-of-00020.safetensors", "model.layers.44.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.44.self_attn.k_norm.weight": "model-00013-of-00020.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.44.self_attn.q_norm.weight": "model-00013-of-00020.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.10.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.10.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.10.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.100.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.100.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.100.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.101.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.101.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.101.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.102.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.102.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.102.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.103.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.103.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.103.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.104.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.104.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.104.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.105.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.105.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.105.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.106.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.106.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.106.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.107.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.107.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.107.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.108.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.108.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.108.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.109.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.109.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.109.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.11.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.11.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.11.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.110.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.110.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.110.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.111.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.111.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.111.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.112.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.112.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.112.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.113.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.113.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.113.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.114.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.114.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.114.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.115.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.115.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.115.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.12.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.12.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.12.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.13.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.13.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.13.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.14.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.14.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.14.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.15.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.15.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.15.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.16.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.16.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.16.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.17.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.17.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.17.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.18.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.18.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.18.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.19.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.19.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.19.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.20.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.20.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.20.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.21.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.21.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.21.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.22.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.22.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.22.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.23.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.23.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.23.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.24.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.24.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.24.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.25.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.25.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.25.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.26.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.26.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.26.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.27.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.27.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.27.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.28.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.28.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.28.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.29.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.29.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.29.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.30.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.30.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.30.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.31.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.31.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.31.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.32.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.32.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.32.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.33.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.33.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.33.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.34.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.34.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.34.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.35.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.35.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.35.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.36.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.36.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.36.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.37.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.37.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.37.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.38.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.38.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.38.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.39.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.39.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.39.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.40.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.40.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.40.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.41.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.41.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.41.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.42.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.42.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.42.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.43.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.43.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.43.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.44.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.44.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.44.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.45.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.45.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.45.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.46.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.46.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.46.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.47.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.47.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.47.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.48.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.48.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.48.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.49.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.49.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.49.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.50.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.50.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.50.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.51.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.51.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.51.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.52.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.52.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.52.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.53.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.53.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.53.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.54.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.54.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.54.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.55.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.55.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.55.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.56.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.56.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.56.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.57.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.57.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.57.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.58.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.58.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.58.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.59.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.59.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.59.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.60.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.60.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.60.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.61.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.61.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.61.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.62.w1.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.62.w2.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.62.w3.weight": "model-00013-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.63.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.63.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.63.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.64.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.64.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.64.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.65.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.65.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.65.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.66.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.66.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.66.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.67.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.67.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.67.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.68.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.68.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.68.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.69.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.69.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.69.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.70.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.70.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.70.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.71.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.71.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.71.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.72.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.72.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.72.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.73.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.73.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.73.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.74.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.74.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.74.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.75.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.75.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.75.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.76.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.76.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.76.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.77.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.77.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.77.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.78.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.78.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.78.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.79.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.79.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.79.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.8.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.8.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.8.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.80.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.80.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.80.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.81.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.81.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.81.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.82.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.82.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.82.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.83.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.83.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.83.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.84.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.84.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.84.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.85.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.85.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.85.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.86.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.86.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.86.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.87.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.87.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.87.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.88.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.88.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.88.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.89.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.89.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.89.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.9.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.9.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.9.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.90.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.90.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.90.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.91.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.91.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.91.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.92.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.92.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.92.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.93.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.93.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.93.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.94.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.94.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.94.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.95.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.95.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.95.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.96.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.96.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.96.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.97.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.97.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.97.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.98.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.98.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.98.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.99.w1.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.99.w2.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.99.w3.weight": "model-00014-of-00020.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00014-of-00020.safetensors", "model.layers.45.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.45.self_attn.k_norm.weight": "model-00014-of-00020.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.45.self_attn.q_norm.weight": "model-00014-of-00020.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.10.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.10.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.10.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.100.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.100.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.100.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.101.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.101.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.101.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.102.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.102.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.102.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.103.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.103.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.103.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.104.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.104.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.104.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.105.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.105.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.105.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.106.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.106.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.106.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.107.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.107.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.107.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.108.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.108.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.108.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.109.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.109.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.109.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.11.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.11.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.11.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.110.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.110.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.110.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.111.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.111.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.111.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.112.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.112.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.112.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.113.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.113.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.113.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.114.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.114.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.114.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.115.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.115.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.115.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.12.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.12.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.12.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.13.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.13.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.13.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.14.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.14.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.14.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.15.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.15.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.15.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.16.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.16.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.16.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.17.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.17.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.17.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.18.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.18.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.18.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.19.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.19.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.19.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.20.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.20.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.20.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.21.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.21.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.21.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.22.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.22.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.22.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.23.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.23.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.23.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.24.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.24.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.24.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.25.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.25.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.25.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.26.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.26.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.26.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.27.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.27.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.27.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.28.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.28.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.28.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.29.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.29.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.29.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.30.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.30.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.30.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.31.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.31.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.31.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.32.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.32.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.32.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.33.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.33.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.33.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.34.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.34.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.34.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.35.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.35.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.35.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.36.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.36.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.36.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.37.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.37.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.37.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.38.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.38.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.38.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.39.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.39.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.39.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.40.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.40.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.40.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.41.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.41.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.41.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.42.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.42.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.42.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.43.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.43.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.43.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.44.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.44.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.44.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.45.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.45.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.45.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.46.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.46.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.46.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.47.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.47.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.47.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.48.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.48.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.48.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.49.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.49.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.49.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.50.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.50.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.50.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.51.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.51.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.51.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.52.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.52.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.52.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.53.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.53.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.53.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.54.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.54.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.54.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.55.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.55.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.55.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.56.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.56.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.56.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.57.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.57.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.57.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.58.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.58.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.58.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.59.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.59.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.59.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.60.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.60.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.60.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.61.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.61.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.61.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.62.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.62.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.62.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.63.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.63.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.63.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.64.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.64.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.64.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.65.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.65.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.65.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.66.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.66.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.66.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.67.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.67.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.67.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.68.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.68.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.68.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.69.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.69.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.69.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.70.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.70.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.70.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.71.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.71.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.71.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.72.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.72.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.72.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.73.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.73.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.73.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.74.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.74.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.74.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.75.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.75.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.75.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.76.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.76.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.76.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.77.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.77.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.77.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.78.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.78.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.78.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.79.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.79.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.79.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.8.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.8.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.8.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.80.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.80.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.80.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.81.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.81.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.81.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.82.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.82.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.82.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.83.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.83.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.83.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.84.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.84.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.84.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.85.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.85.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.85.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.86.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.86.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.86.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.87.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.87.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.87.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.88.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.88.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.88.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.89.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.89.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.89.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.9.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.9.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.9.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.90.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.90.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.90.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.91.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.91.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.91.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.92.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.92.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.92.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.93.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.93.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.93.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.94.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.94.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.94.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.95.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.95.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.95.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.96.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.96.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.96.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.97.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.97.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.97.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.98.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.98.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.98.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.99.w1.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.99.w2.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.99.w3.weight": "model-00014-of-00020.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00014-of-00020.safetensors", "model.layers.46.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.46.self_attn.k_norm.weight": "model-00014-of-00020.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.46.self_attn.q_norm.weight": "model-00014-of-00020.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.10.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.10.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.10.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.100.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.100.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.100.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.101.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.101.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.101.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.102.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.102.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.102.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.103.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.103.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.103.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.104.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.104.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.104.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.105.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.105.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.105.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.106.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.106.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.106.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.107.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.107.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.107.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.108.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.108.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.108.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.109.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.109.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.109.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.11.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.11.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.11.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.110.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.110.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.110.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.111.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.111.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.111.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.112.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.112.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.112.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.113.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.113.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.113.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.114.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.114.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.114.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.115.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.115.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.115.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.12.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.12.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.12.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.13.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.13.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.13.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.14.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.14.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.14.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.15.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.15.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.15.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.16.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.16.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.16.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.17.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.17.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.17.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.18.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.18.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.18.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.19.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.19.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.19.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.20.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.20.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.20.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.21.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.21.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.21.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.22.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.22.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.22.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.23.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.23.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.23.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.24.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.24.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.24.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.25.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.25.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.25.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.26.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.26.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.26.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.27.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.27.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.27.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.28.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.28.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.28.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.29.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.29.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.29.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.30.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.30.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.30.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.31.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.31.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.31.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.32.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.32.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.32.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.33.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.33.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.33.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.34.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.34.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.34.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.35.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.35.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.35.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.36.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.36.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.36.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.37.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.37.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.37.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.38.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.38.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.38.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.39.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.39.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.39.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.40.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.40.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.40.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.41.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.41.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.41.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.42.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.42.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.42.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.43.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.43.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.43.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.44.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.44.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.44.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.45.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.45.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.45.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.46.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.46.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.46.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.47.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.47.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.47.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.48.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.48.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.48.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.49.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.49.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.49.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.50.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.50.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.50.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.51.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.51.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.51.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.52.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.52.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.52.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.53.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.53.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.53.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.54.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.54.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.54.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.55.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.55.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.55.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.56.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.56.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.56.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.57.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.57.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.57.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.58.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.58.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.58.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.59.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.59.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.59.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.60.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.60.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.60.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.61.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.61.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.61.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.62.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.62.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.62.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.63.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.63.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.63.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.64.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.64.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.64.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.65.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.65.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.65.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.66.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.66.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.66.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.67.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.67.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.67.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.68.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.68.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.68.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.69.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.69.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.69.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.70.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.70.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.70.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.71.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.71.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.71.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.72.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.72.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.72.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.73.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.73.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.73.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.74.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.74.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.74.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.75.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.75.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.75.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.76.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.76.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.76.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.77.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.77.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.77.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.78.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.78.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.78.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.79.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.79.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.79.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.8.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.8.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.8.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.80.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.80.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.80.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.81.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.81.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.81.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.82.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.82.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.82.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.83.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.83.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.83.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.84.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.84.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.84.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.85.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.85.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.85.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.86.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.86.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.86.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.87.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.87.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.87.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.88.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.88.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.88.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.89.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.89.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.89.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.9.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.9.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.9.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.90.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.90.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.90.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.91.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.91.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.91.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.92.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.92.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.92.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.93.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.93.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.93.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.94.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.94.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.94.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.95.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.95.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.95.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.96.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.96.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.96.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.97.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.97.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.97.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.98.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.98.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.98.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.99.w1.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.99.w2.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.99.w3.weight": "model-00014-of-00020.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00014-of-00020.safetensors", "model.layers.47.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.47.self_attn.k_norm.weight": "model-00014-of-00020.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.47.self_attn.q_norm.weight": "model-00014-of-00020.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.10.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.10.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.10.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.100.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.100.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.100.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.101.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.101.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.101.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.102.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.102.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.102.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.103.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.103.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.103.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.104.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.104.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.104.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.105.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.105.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.105.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.106.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.106.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.106.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.107.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.107.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.107.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.108.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.108.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.108.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.109.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.109.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.109.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.11.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.11.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.11.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.110.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.110.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.110.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.111.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.111.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.111.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.112.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.112.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.112.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.113.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.113.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.113.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.114.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.114.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.114.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.115.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.115.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.115.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.12.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.12.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.12.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.13.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.13.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.13.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.14.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.14.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.14.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.15.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.15.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.15.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.16.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.16.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.16.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.17.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.17.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.17.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.18.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.18.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.18.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.19.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.19.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.19.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.20.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.20.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.20.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.21.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.21.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.21.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.22.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.22.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.22.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.23.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.23.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.23.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.24.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.24.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.24.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.25.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.25.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.25.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.26.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.26.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.26.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.27.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.27.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.27.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.28.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.28.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.28.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.29.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.29.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.29.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.30.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.30.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.30.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.31.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.31.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.31.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.32.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.32.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.32.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.33.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.33.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.33.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.34.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.34.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.34.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.35.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.35.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.35.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.36.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.36.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.36.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.37.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.37.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.37.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.38.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.38.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.38.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.39.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.39.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.39.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.40.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.40.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.40.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.41.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.41.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.41.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.42.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.42.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.42.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.43.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.43.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.43.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.44.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.44.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.44.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.45.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.45.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.45.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.46.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.46.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.46.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.47.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.47.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.47.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.48.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.48.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.48.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.49.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.49.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.49.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.50.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.50.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.50.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.51.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.51.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.51.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.52.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.52.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.52.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.53.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.53.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.53.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.54.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.54.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.54.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.55.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.55.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.55.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.56.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.56.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.56.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.57.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.57.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.57.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.58.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.58.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.58.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.59.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.59.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.59.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.60.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.60.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.60.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.61.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.61.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.61.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.62.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.62.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.62.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.63.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.63.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.63.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.64.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.64.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.64.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.65.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.65.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.65.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.66.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.66.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.66.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.67.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.67.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.67.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.68.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.68.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.68.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.69.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.69.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.69.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.70.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.70.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.70.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.71.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.71.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.71.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.72.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.72.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.72.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.73.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.73.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.73.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.74.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.74.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.74.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.75.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.75.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.75.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.76.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.76.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.76.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.77.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.77.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.77.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.78.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.78.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.78.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.79.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.79.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.79.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.8.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.8.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.8.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.80.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.80.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.80.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.81.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.81.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.81.w3.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.82.w1.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.82.w2.weight": "model-00014-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.82.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.83.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.83.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.83.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.84.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.84.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.84.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.85.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.85.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.85.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.86.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.86.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.86.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.87.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.87.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.87.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.88.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.88.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.88.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.89.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.89.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.89.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.9.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.9.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.9.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.90.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.90.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.90.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.91.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.91.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.91.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.92.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.92.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.92.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.93.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.93.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.93.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.94.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.94.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.94.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.95.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.95.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.95.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.96.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.96.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.96.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.97.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.97.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.97.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.98.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.98.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.98.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.99.w1.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.99.w2.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.experts.99.w3.weight": "model-00015-of-00020.safetensors", "model.layers.48.block_sparse_moe.gate.weight": "model-00015-of-00020.safetensors", "model.layers.48.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.48.self_attn.k_norm.weight": "model-00015-of-00020.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.48.self_attn.q_norm.weight": "model-00015-of-00020.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.10.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.10.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.10.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.100.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.100.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.100.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.101.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.101.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.101.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.102.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.102.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.102.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.103.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.103.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.103.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.104.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.104.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.104.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.105.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.105.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.105.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.106.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.106.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.106.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.107.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.107.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.107.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.108.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.108.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.108.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.109.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.109.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.109.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.11.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.11.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.11.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.110.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.110.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.110.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.111.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.111.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.111.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.112.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.112.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.112.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.113.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.113.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.113.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.114.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.114.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.114.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.115.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.115.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.115.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.12.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.12.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.12.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.13.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.13.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.13.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.14.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.14.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.14.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.15.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.15.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.15.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.16.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.16.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.16.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.17.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.17.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.17.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.18.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.18.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.18.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.19.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.19.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.19.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.20.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.20.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.20.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.21.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.21.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.21.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.22.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.22.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.22.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.23.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.23.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.23.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.24.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.24.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.24.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.25.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.25.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.25.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.26.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.26.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.26.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.27.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.27.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.27.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.28.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.28.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.28.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.29.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.29.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.29.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.30.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.30.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.30.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.31.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.31.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.31.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.32.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.32.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.32.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.33.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.33.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.33.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.34.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.34.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.34.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.35.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.35.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.35.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.36.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.36.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.36.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.37.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.37.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.37.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.38.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.38.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.38.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.39.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.39.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.39.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.40.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.40.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.40.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.41.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.41.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.41.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.42.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.42.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.42.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.43.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.43.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.43.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.44.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.44.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.44.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.45.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.45.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.45.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.46.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.46.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.46.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.47.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.47.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.47.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.48.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.48.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.48.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.49.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.49.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.49.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.50.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.50.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.50.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.51.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.51.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.51.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.52.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.52.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.52.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.53.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.53.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.53.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.54.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.54.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.54.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.55.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.55.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.55.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.56.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.56.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.56.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.57.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.57.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.57.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.58.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.58.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.58.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.59.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.59.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.59.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.60.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.60.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.60.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.61.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.61.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.61.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.62.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.62.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.62.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.63.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.63.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.63.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.64.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.64.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.64.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.65.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.65.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.65.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.66.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.66.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.66.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.67.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.67.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.67.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.68.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.68.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.68.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.69.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.69.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.69.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.70.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.70.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.70.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.71.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.71.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.71.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.72.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.72.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.72.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.73.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.73.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.73.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.74.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.74.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.74.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.75.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.75.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.75.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.76.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.76.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.76.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.77.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.77.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.77.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.78.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.78.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.78.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.79.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.79.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.79.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.8.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.8.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.8.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.80.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.80.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.80.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.81.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.81.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.81.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.82.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.82.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.82.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.83.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.83.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.83.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.84.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.84.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.84.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.85.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.85.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.85.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.86.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.86.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.86.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.87.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.87.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.87.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.88.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.88.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.88.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.89.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.89.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.89.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.9.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.9.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.9.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.90.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.90.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.90.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.91.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.91.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.91.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.92.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.92.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.92.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.93.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.93.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.93.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.94.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.94.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.94.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.95.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.95.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.95.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.96.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.96.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.96.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.97.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.97.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.97.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.98.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.98.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.98.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.99.w1.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.99.w2.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.experts.99.w3.weight": "model-00015-of-00020.safetensors", "model.layers.49.block_sparse_moe.gate.weight": "model-00015-of-00020.safetensors", "model.layers.49.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.49.self_attn.k_norm.weight": "model-00015-of-00020.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.49.self_attn.q_norm.weight": "model-00015-of-00020.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.10.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.10.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.10.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.100.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.100.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.100.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.101.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.101.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.101.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.102.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.102.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.102.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.103.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.103.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.103.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.104.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.104.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.104.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.105.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.105.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.105.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.106.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.106.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.106.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.107.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.107.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.107.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.108.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.108.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.108.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.109.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.109.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.109.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.11.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.11.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.11.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.110.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.110.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.110.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.111.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.111.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.111.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.112.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.112.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.112.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.113.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.113.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.113.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.114.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.114.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.114.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.115.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.115.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.115.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.12.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.12.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.12.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.13.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.13.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.13.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.14.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.14.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.14.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.15.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.15.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.15.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.16.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.16.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.16.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.17.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.17.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.17.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.18.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.18.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.18.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.19.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.19.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.19.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.20.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.20.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.20.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.21.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.21.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.21.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.22.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.22.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.22.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.23.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.23.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.23.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.24.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.24.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.24.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.25.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.25.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.25.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.26.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.26.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.26.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.27.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.27.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.27.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.28.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.28.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.28.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.29.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.29.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.29.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.30.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.30.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.30.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.31.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.31.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.31.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.32.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.32.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.32.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.33.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.33.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.33.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.34.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.34.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.34.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.35.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.35.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.35.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.36.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.36.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.36.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.37.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.37.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.37.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.38.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.38.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.38.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.39.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.39.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.39.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.40.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.40.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.40.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.41.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.41.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.41.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.42.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.42.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.42.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.43.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.43.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.43.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.44.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.44.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.44.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.45.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.45.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.45.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.46.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.46.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.46.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.47.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.47.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.47.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.48.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.48.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.48.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.49.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.49.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.49.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.50.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.50.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.50.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.51.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.51.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.51.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.52.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.52.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.52.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.53.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.53.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.53.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.54.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.54.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.54.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.55.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.55.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.55.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.56.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.56.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.56.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.57.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.57.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.57.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.58.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.58.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.58.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.59.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.59.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.59.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.60.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.60.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.60.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.61.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.61.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.61.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.62.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.62.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.62.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.63.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.63.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.63.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.64.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.64.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.64.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.65.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.65.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.65.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.66.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.66.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.66.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.67.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.67.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.67.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.68.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.68.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.68.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.69.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.69.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.69.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.70.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.70.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.70.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.71.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.71.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.71.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.72.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.72.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.72.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.73.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.73.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.73.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.74.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.74.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.74.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.75.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.75.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.75.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.76.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.76.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.76.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.77.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.77.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.77.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.78.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.78.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.78.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.79.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.79.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.79.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.8.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.8.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.8.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.80.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.80.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.80.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.81.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.81.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.81.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.82.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.82.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.82.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.83.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.83.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.83.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.84.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.84.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.84.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.85.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.85.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.85.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.86.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.86.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.86.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.87.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.87.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.87.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.88.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.88.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.88.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.89.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.89.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.89.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.9.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.9.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.9.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.90.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.90.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.90.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.91.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.91.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.91.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.92.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.92.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.92.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.93.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.93.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.93.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.94.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.94.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.94.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.95.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.95.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.95.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.96.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.96.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.96.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.97.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.97.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.97.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.98.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.98.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.98.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.99.w1.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.99.w2.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.99.w3.weight": "model-00015-of-00020.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00015-of-00020.safetensors", "model.layers.5.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.5.self_attn.k_norm.weight": "model-00015-of-00020.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.5.self_attn.q_norm.weight": "model-00015-of-00020.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.10.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.10.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.10.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.100.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.100.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.100.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.101.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.101.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.101.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.102.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.102.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.102.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.103.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.103.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.103.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.104.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.104.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.104.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.105.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.105.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.105.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.106.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.106.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.106.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.107.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.107.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.107.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.108.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.108.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.108.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.109.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.109.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.109.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.11.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.11.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.11.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.110.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.110.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.110.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.111.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.111.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.111.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.112.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.112.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.112.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.113.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.113.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.113.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.114.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.114.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.114.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.115.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.115.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.115.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.12.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.12.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.12.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.13.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.13.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.13.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.14.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.14.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.14.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.15.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.15.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.15.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.16.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.16.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.16.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.17.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.17.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.17.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.18.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.18.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.18.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.19.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.19.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.19.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.20.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.20.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.20.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.21.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.21.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.21.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.22.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.22.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.22.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.23.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.23.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.23.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.24.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.24.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.24.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.25.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.25.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.25.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.26.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.26.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.26.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.27.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.27.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.27.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.28.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.28.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.28.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.29.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.29.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.29.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.30.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.30.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.30.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.31.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.31.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.31.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.32.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.32.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.32.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.33.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.33.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.33.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.34.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.34.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.34.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.35.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.35.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.35.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.36.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.36.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.36.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.37.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.37.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.37.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.38.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.38.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.38.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.39.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.39.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.39.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.40.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.40.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.40.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.41.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.41.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.41.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.42.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.42.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.42.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.43.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.43.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.43.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.44.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.44.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.44.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.45.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.45.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.45.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.46.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.46.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.46.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.47.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.47.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.47.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.48.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.48.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.48.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.49.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.49.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.49.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.50.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.50.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.50.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.51.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.51.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.51.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.52.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.52.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.52.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.53.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.53.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.53.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.54.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.54.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.54.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.55.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.55.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.55.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.56.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.56.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.56.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.57.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.57.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.57.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.58.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.58.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.58.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.59.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.59.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.59.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.60.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.60.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.60.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.61.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.61.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.61.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.62.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.62.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.62.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.63.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.63.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.63.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.64.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.64.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.64.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.65.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.65.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.65.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.66.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.66.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.66.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.67.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.67.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.67.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.68.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.68.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.68.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.69.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.69.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.69.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.70.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.70.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.70.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.71.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.71.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.71.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.72.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.72.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.72.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.73.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.73.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.73.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.74.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.74.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.74.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.75.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.75.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.75.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.76.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.76.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.76.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.77.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.77.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.77.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.78.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.78.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.78.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.79.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.79.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.79.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.8.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.8.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.8.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.80.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.80.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.80.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.81.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.81.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.81.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.82.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.82.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.82.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.83.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.83.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.83.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.84.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.84.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.84.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.85.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.85.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.85.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.86.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.86.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.86.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.87.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.87.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.87.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.88.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.88.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.88.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.89.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.89.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.89.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.9.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.9.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.9.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.90.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.90.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.90.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.91.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.91.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.91.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.92.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.92.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.92.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.93.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.93.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.93.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.94.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.94.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.94.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.95.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.95.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.95.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.96.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.96.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.96.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.97.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.97.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.97.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.98.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.98.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.98.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.99.w1.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.99.w2.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.experts.99.w3.weight": "model-00015-of-00020.safetensors", "model.layers.50.block_sparse_moe.gate.weight": "model-00015-of-00020.safetensors", "model.layers.50.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.50.self_attn.k_norm.weight": "model-00015-of-00020.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.50.self_attn.q_norm.weight": "model-00015-of-00020.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.10.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.10.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.10.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.100.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.100.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.100.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.101.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.101.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.101.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.102.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.102.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.102.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.103.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.103.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.103.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.104.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.104.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.104.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.105.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.105.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.105.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.106.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.106.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.106.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.107.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.107.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.107.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.108.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.108.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.108.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.109.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.109.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.109.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.11.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.11.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.11.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.110.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.110.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.110.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.111.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.111.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.111.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.112.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.112.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.112.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.113.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.113.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.113.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.114.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.114.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.114.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.115.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.115.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.115.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.12.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.12.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.12.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.13.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.13.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.13.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.14.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.14.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.14.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.15.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.15.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.15.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.16.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.16.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.16.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.17.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.17.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.17.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.18.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.18.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.18.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.19.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.19.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.19.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.20.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.20.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.20.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.21.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.21.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.21.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.22.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.22.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.22.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.23.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.23.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.23.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.24.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.24.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.24.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.25.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.25.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.25.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.26.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.26.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.26.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.27.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.27.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.27.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.28.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.28.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.28.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.29.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.29.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.29.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.30.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.30.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.30.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.31.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.31.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.31.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.32.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.32.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.32.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.33.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.33.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.33.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.34.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.34.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.34.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.35.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.35.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.35.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.36.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.36.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.36.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.37.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.37.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.37.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.38.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.38.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.38.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.39.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.39.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.39.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.40.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.40.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.40.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.41.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.41.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.41.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.42.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.42.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.42.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.43.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.43.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.43.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.44.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.44.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.44.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.45.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.45.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.45.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.46.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.46.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.46.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.47.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.47.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.47.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.48.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.48.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.48.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.49.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.49.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.49.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.50.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.50.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.50.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.51.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.51.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.51.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.52.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.52.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.52.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.53.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.53.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.53.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.54.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.54.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.54.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.55.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.55.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.55.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.56.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.56.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.56.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.57.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.57.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.57.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.58.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.58.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.58.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.59.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.59.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.59.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.60.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.60.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.60.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.61.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.61.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.61.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.62.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.62.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.62.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.63.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.63.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.63.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.64.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.64.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.64.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.65.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.65.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.65.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.66.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.66.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.66.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.67.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.67.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.67.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.68.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.68.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.68.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.69.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.69.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.69.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.70.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.70.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.70.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.71.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.71.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.71.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.72.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.72.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.72.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.73.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.73.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.73.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.74.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.74.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.74.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.75.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.75.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.75.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.76.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.76.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.76.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.77.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.77.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.77.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.78.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.78.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.78.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.79.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.79.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.79.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.8.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.8.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.8.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.80.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.80.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.80.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.81.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.81.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.81.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.82.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.82.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.82.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.83.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.83.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.83.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.84.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.84.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.84.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.85.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.85.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.85.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.86.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.86.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.86.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.87.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.87.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.87.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.88.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.88.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.88.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.89.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.89.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.89.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.9.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.9.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.9.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.90.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.90.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.90.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.91.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.91.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.91.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.92.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.92.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.92.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.93.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.93.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.93.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.94.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.94.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.94.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.95.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.95.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.95.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.96.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.96.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.96.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.97.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.97.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.97.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.98.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.98.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.98.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.99.w1.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.99.w2.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.experts.99.w3.weight": "model-00016-of-00020.safetensors", "model.layers.51.block_sparse_moe.gate.weight": "model-00016-of-00020.safetensors", "model.layers.51.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.51.self_attn.k_norm.weight": "model-00016-of-00020.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.51.self_attn.q_norm.weight": "model-00016-of-00020.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.10.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.10.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.10.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.100.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.100.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.100.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.101.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.101.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.101.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.102.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.102.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.102.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.103.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.103.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.103.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.104.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.104.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.104.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.105.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.105.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.105.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.106.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.106.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.106.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.107.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.107.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.107.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.108.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.108.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.108.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.109.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.109.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.109.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.11.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.11.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.11.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.110.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.110.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.110.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.111.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.111.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.111.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.112.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.112.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.112.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.113.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.113.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.113.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.114.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.114.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.114.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.115.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.115.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.115.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.12.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.12.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.12.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.13.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.13.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.13.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.14.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.14.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.14.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.15.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.15.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.15.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.16.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.16.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.16.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.17.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.17.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.17.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.18.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.18.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.18.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.19.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.19.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.19.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.20.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.20.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.20.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.21.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.21.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.21.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.22.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.22.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.22.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.23.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.23.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.23.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.24.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.24.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.24.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.25.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.25.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.25.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.26.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.26.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.26.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.27.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.27.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.27.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.28.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.28.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.28.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.29.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.29.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.29.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.30.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.30.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.30.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.31.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.31.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.31.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.32.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.32.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.32.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.33.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.33.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.33.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.34.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.34.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.34.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.35.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.35.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.35.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.36.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.36.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.36.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.37.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.37.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.37.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.38.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.38.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.38.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.39.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.39.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.39.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.40.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.40.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.40.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.41.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.41.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.41.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.42.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.42.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.42.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.43.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.43.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.43.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.44.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.44.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.44.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.45.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.45.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.45.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.46.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.46.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.46.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.47.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.47.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.47.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.48.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.48.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.48.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.49.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.49.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.49.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.50.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.50.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.50.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.51.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.51.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.51.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.52.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.52.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.52.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.53.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.53.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.53.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.54.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.54.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.54.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.55.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.55.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.55.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.56.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.56.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.56.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.57.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.57.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.57.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.58.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.58.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.58.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.59.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.59.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.59.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.60.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.60.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.60.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.61.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.61.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.61.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.62.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.62.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.62.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.63.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.63.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.63.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.64.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.64.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.64.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.65.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.65.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.65.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.66.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.66.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.66.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.67.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.67.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.67.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.68.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.68.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.68.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.69.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.69.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.69.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.70.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.70.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.70.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.71.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.71.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.71.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.72.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.72.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.72.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.73.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.73.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.73.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.74.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.74.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.74.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.75.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.75.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.75.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.76.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.76.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.76.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.77.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.77.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.77.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.78.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.78.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.78.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.79.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.79.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.79.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.8.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.8.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.8.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.80.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.80.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.80.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.81.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.81.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.81.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.82.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.82.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.82.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.83.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.83.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.83.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.84.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.84.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.84.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.85.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.85.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.85.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.86.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.86.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.86.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.87.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.87.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.87.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.88.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.88.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.88.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.89.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.89.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.89.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.9.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.9.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.9.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.90.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.90.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.90.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.91.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.91.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.91.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.92.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.92.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.92.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.93.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.93.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.93.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.94.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.94.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.94.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.95.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.95.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.95.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.96.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.96.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.96.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.97.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.97.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.97.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.98.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.98.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.98.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.99.w1.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.99.w2.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.experts.99.w3.weight": "model-00016-of-00020.safetensors", "model.layers.52.block_sparse_moe.gate.weight": "model-00016-of-00020.safetensors", "model.layers.52.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.52.self_attn.k_norm.weight": "model-00016-of-00020.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.52.self_attn.q_norm.weight": "model-00016-of-00020.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.10.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.10.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.10.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.100.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.100.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.100.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.101.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.101.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.101.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.102.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.102.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.102.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.103.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.103.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.103.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.104.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.104.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.104.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.105.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.105.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.105.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.106.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.106.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.106.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.107.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.107.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.107.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.108.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.108.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.108.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.109.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.109.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.109.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.11.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.11.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.11.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.110.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.110.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.110.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.111.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.111.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.111.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.112.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.112.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.112.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.113.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.113.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.113.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.114.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.114.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.114.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.115.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.115.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.115.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.12.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.12.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.12.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.13.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.13.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.13.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.14.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.14.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.14.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.15.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.15.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.15.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.16.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.16.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.16.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.17.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.17.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.17.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.18.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.18.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.18.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.19.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.19.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.19.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.20.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.20.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.20.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.21.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.21.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.21.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.22.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.22.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.22.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.23.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.23.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.23.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.24.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.24.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.24.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.25.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.25.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.25.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.26.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.26.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.26.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.27.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.27.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.27.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.28.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.28.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.28.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.29.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.29.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.29.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.30.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.30.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.30.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.31.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.31.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.31.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.32.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.32.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.32.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.33.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.33.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.33.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.34.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.34.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.34.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.35.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.35.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.35.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.36.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.36.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.36.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.37.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.37.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.37.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.38.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.38.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.38.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.39.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.39.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.39.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.40.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.40.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.40.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.41.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.41.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.41.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.42.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.42.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.42.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.43.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.43.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.43.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.44.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.44.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.44.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.45.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.45.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.45.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.46.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.46.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.46.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.47.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.47.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.47.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.48.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.48.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.48.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.49.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.49.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.49.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.50.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.50.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.50.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.51.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.51.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.51.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.52.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.52.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.52.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.53.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.53.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.53.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.54.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.54.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.54.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.55.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.55.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.55.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.56.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.56.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.56.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.57.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.57.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.57.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.58.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.58.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.58.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.59.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.59.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.59.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.60.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.60.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.60.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.61.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.61.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.61.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.62.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.62.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.62.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.63.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.63.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.63.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.64.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.64.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.64.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.65.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.65.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.65.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.66.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.66.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.66.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.67.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.67.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.67.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.68.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.68.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.68.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.69.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.69.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.69.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.70.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.70.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.70.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.71.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.71.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.71.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.72.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.72.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.72.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.73.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.73.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.73.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.74.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.74.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.74.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.75.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.75.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.75.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.76.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.76.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.76.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.77.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.77.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.77.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.78.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.78.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.78.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.79.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.79.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.79.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.8.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.8.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.8.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.80.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.80.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.80.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.81.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.81.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.81.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.82.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.82.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.82.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.83.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.83.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.83.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.84.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.84.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.84.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.85.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.85.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.85.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.86.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.86.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.86.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.87.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.87.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.87.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.88.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.88.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.88.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.89.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.89.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.89.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.9.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.9.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.9.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.90.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.90.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.90.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.91.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.91.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.91.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.92.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.92.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.92.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.93.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.93.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.93.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.94.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.94.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.94.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.95.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.95.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.95.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.96.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.96.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.96.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.97.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.97.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.97.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.98.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.98.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.98.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.99.w1.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.99.w2.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.experts.99.w3.weight": "model-00016-of-00020.safetensors", "model.layers.53.block_sparse_moe.gate.weight": "model-00016-of-00020.safetensors", "model.layers.53.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.53.self_attn.k_norm.weight": "model-00016-of-00020.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.53.self_attn.q_norm.weight": "model-00016-of-00020.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.10.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.10.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.10.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.100.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.100.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.100.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.101.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.101.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.101.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.102.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.102.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.102.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.103.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.103.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.103.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.104.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.104.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.104.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.105.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.105.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.105.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.106.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.106.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.106.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.107.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.107.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.107.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.108.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.108.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.108.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.109.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.109.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.109.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.11.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.11.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.11.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.110.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.110.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.110.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.111.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.111.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.111.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.112.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.112.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.112.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.113.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.113.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.113.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.114.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.114.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.114.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.115.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.115.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.115.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.12.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.12.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.12.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.13.w1.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.13.w2.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.13.w3.weight": "model-00016-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.14.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.14.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.14.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.15.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.15.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.15.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.16.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.16.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.16.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.17.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.17.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.17.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.18.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.18.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.18.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.19.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.19.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.19.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.20.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.20.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.20.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.21.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.21.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.21.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.22.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.22.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.22.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.23.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.23.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.23.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.24.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.24.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.24.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.25.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.25.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.25.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.26.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.26.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.26.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.27.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.27.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.27.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.28.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.28.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.28.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.29.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.29.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.29.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.30.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.30.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.30.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.31.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.31.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.31.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.32.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.32.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.32.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.33.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.33.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.33.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.34.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.34.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.34.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.35.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.35.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.35.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.36.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.36.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.36.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.37.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.37.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.37.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.38.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.38.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.38.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.39.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.39.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.39.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.40.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.40.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.40.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.41.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.41.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.41.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.42.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.42.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.42.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.43.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.43.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.43.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.44.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.44.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.44.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.45.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.45.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.45.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.46.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.46.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.46.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.47.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.47.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.47.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.48.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.48.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.48.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.49.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.49.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.49.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.50.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.50.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.50.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.51.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.51.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.51.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.52.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.52.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.52.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.53.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.53.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.53.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.54.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.54.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.54.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.55.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.55.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.55.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.56.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.56.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.56.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.57.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.57.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.57.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.58.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.58.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.58.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.59.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.59.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.59.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.60.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.60.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.60.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.61.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.61.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.61.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.62.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.62.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.62.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.63.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.63.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.63.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.64.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.64.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.64.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.65.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.65.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.65.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.66.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.66.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.66.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.67.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.67.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.67.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.68.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.68.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.68.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.69.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.69.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.69.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.70.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.70.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.70.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.71.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.71.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.71.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.72.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.72.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.72.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.73.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.73.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.73.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.74.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.74.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.74.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.75.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.75.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.75.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.76.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.76.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.76.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.77.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.77.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.77.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.78.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.78.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.78.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.79.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.79.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.79.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.8.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.8.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.8.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.80.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.80.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.80.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.81.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.81.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.81.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.82.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.82.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.82.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.83.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.83.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.83.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.84.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.84.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.84.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.85.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.85.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.85.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.86.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.86.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.86.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.87.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.87.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.87.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.88.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.88.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.88.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.89.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.89.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.89.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.9.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.9.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.9.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.90.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.90.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.90.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.91.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.91.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.91.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.92.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.92.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.92.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.93.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.93.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.93.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.94.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.94.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.94.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.95.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.95.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.95.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.96.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.96.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.96.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.97.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.97.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.97.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.98.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.98.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.98.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.99.w1.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.99.w2.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.experts.99.w3.weight": "model-00017-of-00020.safetensors", "model.layers.54.block_sparse_moe.gate.weight": "model-00017-of-00020.safetensors", "model.layers.54.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.54.self_attn.k_norm.weight": "model-00017-of-00020.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.54.self_attn.q_norm.weight": "model-00017-of-00020.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.10.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.10.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.10.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.100.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.100.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.100.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.101.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.101.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.101.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.102.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.102.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.102.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.103.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.103.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.103.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.104.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.104.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.104.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.105.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.105.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.105.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.106.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.106.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.106.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.107.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.107.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.107.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.108.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.108.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.108.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.109.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.109.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.109.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.11.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.11.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.11.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.110.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.110.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.110.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.111.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.111.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.111.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.112.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.112.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.112.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.113.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.113.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.113.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.114.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.114.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.114.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.115.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.115.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.115.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.12.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.12.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.12.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.13.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.13.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.13.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.14.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.14.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.14.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.15.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.15.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.15.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.16.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.16.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.16.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.17.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.17.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.17.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.18.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.18.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.18.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.19.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.19.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.19.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.20.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.20.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.20.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.21.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.21.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.21.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.22.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.22.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.22.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.23.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.23.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.23.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.24.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.24.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.24.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.25.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.25.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.25.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.26.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.26.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.26.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.27.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.27.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.27.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.28.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.28.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.28.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.29.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.29.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.29.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.30.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.30.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.30.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.31.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.31.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.31.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.32.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.32.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.32.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.33.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.33.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.33.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.34.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.34.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.34.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.35.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.35.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.35.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.36.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.36.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.36.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.37.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.37.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.37.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.38.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.38.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.38.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.39.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.39.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.39.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.40.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.40.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.40.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.41.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.41.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.41.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.42.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.42.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.42.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.43.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.43.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.43.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.44.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.44.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.44.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.45.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.45.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.45.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.46.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.46.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.46.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.47.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.47.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.47.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.48.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.48.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.48.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.49.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.49.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.49.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.50.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.50.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.50.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.51.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.51.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.51.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.52.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.52.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.52.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.53.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.53.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.53.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.54.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.54.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.54.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.55.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.55.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.55.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.56.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.56.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.56.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.57.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.57.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.57.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.58.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.58.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.58.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.59.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.59.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.59.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.60.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.60.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.60.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.61.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.61.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.61.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.62.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.62.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.62.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.63.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.63.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.63.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.64.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.64.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.64.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.65.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.65.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.65.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.66.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.66.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.66.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.67.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.67.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.67.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.68.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.68.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.68.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.69.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.69.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.69.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.70.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.70.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.70.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.71.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.71.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.71.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.72.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.72.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.72.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.73.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.73.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.73.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.74.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.74.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.74.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.75.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.75.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.75.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.76.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.76.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.76.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.77.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.77.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.77.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.78.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.78.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.78.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.79.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.79.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.79.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.8.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.8.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.8.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.80.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.80.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.80.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.81.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.81.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.81.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.82.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.82.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.82.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.83.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.83.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.83.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.84.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.84.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.84.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.85.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.85.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.85.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.86.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.86.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.86.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.87.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.87.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.87.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.88.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.88.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.88.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.89.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.89.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.89.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.9.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.9.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.9.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.90.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.90.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.90.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.91.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.91.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.91.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.92.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.92.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.92.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.93.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.93.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.93.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.94.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.94.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.94.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.95.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.95.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.95.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.96.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.96.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.96.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.97.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.97.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.97.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.98.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.98.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.98.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.99.w1.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.99.w2.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.experts.99.w3.weight": "model-00017-of-00020.safetensors", "model.layers.55.block_sparse_moe.gate.weight": "model-00017-of-00020.safetensors", "model.layers.55.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.55.self_attn.k_norm.weight": "model-00017-of-00020.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.55.self_attn.q_norm.weight": "model-00017-of-00020.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.10.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.10.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.10.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.100.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.100.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.100.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.101.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.101.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.101.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.102.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.102.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.102.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.103.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.103.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.103.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.104.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.104.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.104.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.105.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.105.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.105.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.106.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.106.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.106.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.107.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.107.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.107.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.108.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.108.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.108.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.109.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.109.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.109.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.11.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.11.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.11.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.110.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.110.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.110.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.111.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.111.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.111.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.112.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.112.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.112.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.113.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.113.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.113.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.114.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.114.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.114.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.115.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.115.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.115.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.12.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.12.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.12.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.13.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.13.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.13.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.14.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.14.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.14.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.15.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.15.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.15.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.16.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.16.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.16.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.17.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.17.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.17.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.18.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.18.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.18.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.19.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.19.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.19.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.20.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.20.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.20.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.21.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.21.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.21.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.22.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.22.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.22.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.23.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.23.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.23.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.24.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.24.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.24.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.25.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.25.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.25.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.26.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.26.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.26.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.27.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.27.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.27.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.28.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.28.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.28.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.29.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.29.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.29.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.30.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.30.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.30.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.31.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.31.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.31.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.32.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.32.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.32.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.33.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.33.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.33.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.34.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.34.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.34.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.35.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.35.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.35.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.36.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.36.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.36.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.37.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.37.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.37.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.38.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.38.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.38.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.39.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.39.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.39.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.40.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.40.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.40.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.41.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.41.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.41.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.42.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.42.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.42.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.43.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.43.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.43.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.44.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.44.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.44.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.45.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.45.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.45.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.46.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.46.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.46.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.47.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.47.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.47.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.48.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.48.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.48.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.49.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.49.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.49.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.50.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.50.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.50.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.51.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.51.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.51.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.52.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.52.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.52.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.53.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.53.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.53.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.54.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.54.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.54.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.55.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.55.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.55.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.56.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.56.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.56.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.57.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.57.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.57.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.58.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.58.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.58.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.59.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.59.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.59.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.60.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.60.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.60.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.61.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.61.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.61.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.62.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.62.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.62.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.63.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.63.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.63.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.64.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.64.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.64.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.65.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.65.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.65.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.66.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.66.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.66.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.67.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.67.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.67.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.68.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.68.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.68.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.69.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.69.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.69.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.70.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.70.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.70.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.71.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.71.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.71.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.72.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.72.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.72.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.73.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.73.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.73.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.74.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.74.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.74.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.75.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.75.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.75.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.76.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.76.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.76.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.77.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.77.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.77.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.78.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.78.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.78.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.79.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.79.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.79.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.8.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.8.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.8.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.80.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.80.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.80.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.81.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.81.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.81.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.82.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.82.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.82.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.83.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.83.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.83.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.84.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.84.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.84.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.85.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.85.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.85.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.86.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.86.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.86.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.87.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.87.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.87.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.88.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.88.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.88.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.89.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.89.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.89.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.9.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.9.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.9.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.90.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.90.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.90.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.91.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.91.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.91.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.92.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.92.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.92.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.93.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.93.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.93.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.94.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.94.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.94.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.95.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.95.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.95.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.96.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.96.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.96.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.97.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.97.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.97.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.98.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.98.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.98.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.99.w1.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.99.w2.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.experts.99.w3.weight": "model-00017-of-00020.safetensors", "model.layers.56.block_sparse_moe.gate.weight": "model-00017-of-00020.safetensors", "model.layers.56.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.56.self_attn.k_norm.weight": "model-00017-of-00020.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.56.self_attn.q_norm.weight": "model-00017-of-00020.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.10.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.10.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.10.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.100.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.100.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.100.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.101.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.101.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.101.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.102.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.102.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.102.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.103.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.103.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.103.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.104.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.104.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.104.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.105.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.105.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.105.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.106.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.106.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.106.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.107.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.107.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.107.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.108.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.108.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.108.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.109.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.109.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.109.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.11.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.11.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.11.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.110.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.110.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.110.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.111.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.111.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.111.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.112.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.112.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.112.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.113.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.113.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.113.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.114.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.114.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.114.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.115.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.115.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.115.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.12.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.12.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.12.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.13.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.13.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.13.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.14.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.14.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.14.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.15.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.15.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.15.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.16.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.16.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.16.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.17.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.17.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.17.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.18.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.18.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.18.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.19.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.19.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.19.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.20.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.20.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.20.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.21.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.21.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.21.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.22.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.22.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.22.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.23.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.23.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.23.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.24.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.24.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.24.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.25.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.25.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.25.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.26.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.26.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.26.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.27.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.27.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.27.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.28.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.28.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.28.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.29.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.29.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.29.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.30.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.30.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.30.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.31.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.31.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.31.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.32.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.32.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.32.w3.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.33.w1.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.33.w2.weight": "model-00017-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.33.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.34.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.34.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.34.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.35.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.35.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.35.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.36.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.36.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.36.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.37.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.37.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.37.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.38.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.38.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.38.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.39.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.39.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.39.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.40.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.40.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.40.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.41.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.41.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.41.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.42.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.42.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.42.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.43.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.43.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.43.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.44.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.44.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.44.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.45.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.45.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.45.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.46.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.46.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.46.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.47.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.47.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.47.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.48.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.48.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.48.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.49.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.49.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.49.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.50.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.50.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.50.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.51.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.51.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.51.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.52.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.52.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.52.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.53.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.53.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.53.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.54.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.54.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.54.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.55.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.55.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.55.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.56.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.56.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.56.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.57.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.57.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.57.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.58.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.58.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.58.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.59.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.59.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.59.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.60.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.60.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.60.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.61.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.61.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.61.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.62.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.62.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.62.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.63.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.63.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.63.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.64.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.64.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.64.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.65.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.65.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.65.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.66.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.66.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.66.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.67.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.67.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.67.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.68.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.68.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.68.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.69.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.69.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.69.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.70.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.70.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.70.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.71.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.71.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.71.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.72.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.72.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.72.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.73.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.73.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.73.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.74.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.74.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.74.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.75.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.75.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.75.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.76.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.76.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.76.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.77.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.77.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.77.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.78.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.78.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.78.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.79.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.79.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.79.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.8.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.8.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.8.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.80.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.80.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.80.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.81.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.81.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.81.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.82.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.82.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.82.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.83.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.83.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.83.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.84.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.84.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.84.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.85.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.85.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.85.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.86.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.86.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.86.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.87.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.87.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.87.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.88.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.88.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.88.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.89.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.89.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.89.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.9.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.9.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.9.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.90.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.90.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.90.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.91.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.91.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.91.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.92.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.92.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.92.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.93.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.93.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.93.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.94.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.94.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.94.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.95.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.95.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.95.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.96.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.96.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.96.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.97.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.97.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.97.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.98.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.98.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.98.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.99.w1.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.99.w2.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.experts.99.w3.weight": "model-00018-of-00020.safetensors", "model.layers.57.block_sparse_moe.gate.weight": "model-00018-of-00020.safetensors", "model.layers.57.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.57.self_attn.k_norm.weight": "model-00018-of-00020.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.57.self_attn.q_norm.weight": "model-00018-of-00020.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.10.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.10.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.10.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.100.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.100.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.100.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.101.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.101.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.101.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.102.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.102.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.102.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.103.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.103.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.103.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.104.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.104.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.104.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.105.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.105.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.105.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.106.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.106.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.106.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.107.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.107.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.107.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.108.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.108.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.108.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.109.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.109.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.109.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.11.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.11.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.11.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.110.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.110.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.110.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.111.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.111.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.111.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.112.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.112.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.112.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.113.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.113.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.113.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.114.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.114.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.114.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.115.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.115.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.115.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.12.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.12.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.12.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.13.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.13.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.13.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.14.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.14.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.14.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.15.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.15.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.15.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.16.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.16.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.16.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.17.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.17.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.17.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.18.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.18.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.18.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.19.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.19.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.19.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.20.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.20.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.20.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.21.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.21.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.21.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.22.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.22.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.22.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.23.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.23.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.23.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.24.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.24.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.24.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.25.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.25.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.25.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.26.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.26.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.26.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.27.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.27.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.27.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.28.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.28.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.28.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.29.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.29.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.29.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.30.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.30.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.30.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.31.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.31.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.31.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.32.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.32.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.32.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.33.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.33.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.33.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.34.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.34.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.34.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.35.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.35.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.35.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.36.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.36.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.36.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.37.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.37.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.37.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.38.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.38.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.38.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.39.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.39.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.39.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.40.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.40.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.40.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.41.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.41.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.41.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.42.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.42.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.42.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.43.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.43.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.43.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.44.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.44.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.44.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.45.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.45.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.45.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.46.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.46.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.46.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.47.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.47.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.47.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.48.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.48.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.48.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.49.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.49.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.49.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.50.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.50.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.50.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.51.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.51.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.51.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.52.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.52.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.52.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.53.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.53.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.53.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.54.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.54.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.54.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.55.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.55.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.55.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.56.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.56.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.56.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.57.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.57.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.57.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.58.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.58.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.58.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.59.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.59.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.59.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.60.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.60.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.60.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.61.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.61.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.61.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.62.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.62.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.62.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.63.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.63.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.63.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.64.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.64.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.64.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.65.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.65.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.65.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.66.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.66.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.66.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.67.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.67.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.67.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.68.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.68.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.68.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.69.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.69.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.69.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.70.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.70.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.70.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.71.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.71.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.71.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.72.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.72.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.72.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.73.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.73.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.73.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.74.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.74.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.74.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.75.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.75.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.75.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.76.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.76.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.76.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.77.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.77.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.77.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.78.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.78.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.78.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.79.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.79.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.79.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.8.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.8.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.8.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.80.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.80.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.80.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.81.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.81.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.81.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.82.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.82.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.82.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.83.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.83.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.83.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.84.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.84.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.84.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.85.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.85.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.85.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.86.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.86.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.86.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.87.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.87.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.87.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.88.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.88.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.88.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.89.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.89.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.89.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.9.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.9.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.9.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.90.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.90.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.90.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.91.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.91.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.91.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.92.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.92.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.92.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.93.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.93.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.93.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.94.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.94.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.94.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.95.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.95.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.95.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.96.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.96.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.96.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.97.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.97.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.97.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.98.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.98.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.98.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.99.w1.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.99.w2.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.experts.99.w3.weight": "model-00018-of-00020.safetensors", "model.layers.58.block_sparse_moe.gate.weight": "model-00018-of-00020.safetensors", "model.layers.58.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.58.self_attn.k_norm.weight": "model-00018-of-00020.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.58.self_attn.q_norm.weight": "model-00018-of-00020.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.10.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.10.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.10.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.100.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.100.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.100.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.101.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.101.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.101.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.102.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.102.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.102.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.103.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.103.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.103.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.104.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.104.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.104.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.105.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.105.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.105.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.106.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.106.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.106.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.107.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.107.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.107.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.108.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.108.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.108.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.109.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.109.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.109.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.11.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.11.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.11.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.110.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.110.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.110.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.111.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.111.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.111.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.112.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.112.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.112.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.113.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.113.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.113.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.114.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.114.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.114.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.115.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.115.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.115.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.12.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.12.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.12.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.13.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.13.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.13.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.14.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.14.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.14.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.15.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.15.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.15.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.16.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.16.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.16.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.17.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.17.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.17.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.18.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.18.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.18.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.19.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.19.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.19.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.20.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.20.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.20.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.21.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.21.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.21.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.22.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.22.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.22.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.23.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.23.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.23.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.24.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.24.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.24.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.25.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.25.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.25.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.26.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.26.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.26.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.27.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.27.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.27.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.28.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.28.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.28.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.29.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.29.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.29.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.30.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.30.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.30.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.31.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.31.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.31.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.32.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.32.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.32.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.33.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.33.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.33.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.34.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.34.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.34.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.35.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.35.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.35.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.36.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.36.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.36.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.37.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.37.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.37.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.38.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.38.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.38.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.39.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.39.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.39.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.40.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.40.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.40.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.41.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.41.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.41.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.42.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.42.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.42.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.43.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.43.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.43.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.44.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.44.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.44.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.45.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.45.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.45.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.46.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.46.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.46.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.47.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.47.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.47.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.48.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.48.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.48.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.49.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.49.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.49.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.50.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.50.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.50.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.51.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.51.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.51.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.52.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.52.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.52.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.53.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.53.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.53.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.54.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.54.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.54.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.55.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.55.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.55.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.56.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.56.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.56.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.57.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.57.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.57.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.58.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.58.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.58.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.59.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.59.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.59.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.60.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.60.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.60.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.61.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.61.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.61.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.62.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.62.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.62.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.63.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.63.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.63.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.64.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.64.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.64.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.65.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.65.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.65.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.66.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.66.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.66.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.67.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.67.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.67.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.68.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.68.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.68.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.69.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.69.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.69.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.70.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.70.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.70.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.71.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.71.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.71.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.72.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.72.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.72.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.73.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.73.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.73.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.74.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.74.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.74.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.75.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.75.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.75.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.76.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.76.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.76.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.77.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.77.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.77.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.78.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.78.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.78.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.79.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.79.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.79.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.8.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.8.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.8.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.80.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.80.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.80.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.81.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.81.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.81.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.82.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.82.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.82.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.83.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.83.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.83.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.84.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.84.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.84.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.85.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.85.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.85.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.86.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.86.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.86.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.87.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.87.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.87.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.88.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.88.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.88.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.89.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.89.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.89.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.9.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.9.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.9.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.90.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.90.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.90.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.91.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.91.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.91.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.92.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.92.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.92.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.93.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.93.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.93.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.94.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.94.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.94.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.95.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.95.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.95.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.96.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.96.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.96.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.97.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.97.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.97.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.98.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.98.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.98.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.99.w1.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.99.w2.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.experts.99.w3.weight": "model-00018-of-00020.safetensors", "model.layers.59.block_sparse_moe.gate.weight": "model-00018-of-00020.safetensors", "model.layers.59.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.59.self_attn.k_norm.weight": "model-00018-of-00020.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.59.self_attn.q_norm.weight": "model-00018-of-00020.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.10.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.10.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.10.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.100.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.100.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.100.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.101.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.101.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.101.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.102.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.102.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.102.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.103.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.103.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.103.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.104.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.104.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.104.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.105.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.105.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.105.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.106.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.106.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.106.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.107.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.107.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.107.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.108.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.108.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.108.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.109.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.109.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.109.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.11.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.11.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.11.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.110.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.110.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.110.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.111.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.111.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.111.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.112.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.112.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.112.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.113.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.113.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.113.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.114.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.114.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.114.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.115.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.115.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.115.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.12.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.12.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.12.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.13.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.13.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.13.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.14.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.14.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.14.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.15.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.15.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.15.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.16.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.16.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.16.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.17.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.17.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.17.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.18.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.18.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.18.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.19.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.19.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.19.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.20.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.20.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.20.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.21.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.21.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.21.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.22.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.22.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.22.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.23.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.23.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.23.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.24.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.24.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.24.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.25.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.25.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.25.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.26.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.26.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.26.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.27.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.27.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.27.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.28.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.28.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.28.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.29.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.29.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.29.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.30.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.30.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.30.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.31.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.31.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.31.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.32.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.32.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.32.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.33.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.33.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.33.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.34.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.34.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.34.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.35.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.35.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.35.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.36.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.36.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.36.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.37.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.37.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.37.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.38.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.38.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.38.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.39.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.39.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.39.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.40.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.40.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.40.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.41.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.41.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.41.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.42.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.42.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.42.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.43.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.43.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.43.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.44.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.44.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.44.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.45.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.45.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.45.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.46.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.46.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.46.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.47.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.47.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.47.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.48.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.48.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.48.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.49.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.49.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.49.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.50.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.50.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.50.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.51.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.51.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.51.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.52.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.52.w2.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.52.w3.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.53.w1.weight": "model-00018-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.53.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.53.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.54.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.54.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.54.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.55.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.55.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.55.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.56.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.56.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.56.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.57.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.57.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.57.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.58.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.58.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.58.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.59.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.59.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.59.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.60.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.60.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.60.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.61.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.61.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.61.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.62.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.62.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.62.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.63.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.63.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.63.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.64.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.64.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.64.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.65.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.65.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.65.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.66.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.66.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.66.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.67.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.67.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.67.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.68.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.68.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.68.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.69.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.69.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.69.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.70.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.70.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.70.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.71.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.71.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.71.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.72.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.72.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.72.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.73.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.73.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.73.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.74.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.74.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.74.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.75.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.75.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.75.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.76.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.76.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.76.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.77.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.77.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.77.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.78.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.78.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.78.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.79.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.79.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.79.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.8.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.8.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.8.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.80.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.80.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.80.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.81.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.81.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.81.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.82.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.82.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.82.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.83.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.83.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.83.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.84.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.84.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.84.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.85.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.85.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.85.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.86.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.86.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.86.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.87.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.87.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.87.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.88.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.88.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.88.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.89.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.89.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.89.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.9.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.9.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.9.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.90.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.90.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.90.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.91.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.91.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.91.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.92.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.92.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.92.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.93.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.93.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.93.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.94.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.94.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.94.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.95.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.95.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.95.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.96.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.96.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.96.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.97.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.97.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.97.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.98.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.98.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.98.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.99.w1.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.99.w2.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.99.w3.weight": "model-00019-of-00020.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.6.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.k_norm.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.q_norm.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.10.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.10.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.10.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.100.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.100.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.100.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.101.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.101.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.101.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.102.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.102.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.102.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.103.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.103.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.103.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.104.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.104.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.104.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.105.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.105.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.105.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.106.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.106.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.106.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.107.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.107.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.107.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.108.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.108.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.108.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.109.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.109.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.109.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.11.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.11.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.11.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.110.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.110.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.110.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.111.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.111.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.111.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.112.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.112.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.112.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.113.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.113.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.113.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.114.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.114.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.114.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.115.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.115.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.115.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.12.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.12.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.12.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.13.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.13.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.13.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.14.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.14.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.14.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.15.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.15.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.15.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.16.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.16.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.16.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.17.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.17.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.17.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.18.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.18.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.18.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.19.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.19.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.19.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.20.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.20.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.20.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.21.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.21.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.21.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.22.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.22.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.22.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.23.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.23.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.23.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.24.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.24.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.24.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.25.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.25.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.25.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.26.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.26.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.26.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.27.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.27.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.27.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.28.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.28.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.28.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.29.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.29.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.29.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.30.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.30.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.30.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.31.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.31.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.31.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.32.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.32.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.32.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.33.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.33.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.33.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.34.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.34.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.34.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.35.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.35.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.35.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.36.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.36.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.36.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.37.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.37.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.37.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.38.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.38.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.38.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.39.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.39.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.39.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.40.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.40.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.40.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.41.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.41.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.41.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.42.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.42.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.42.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.43.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.43.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.43.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.44.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.44.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.44.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.45.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.45.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.45.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.46.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.46.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.46.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.47.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.47.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.47.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.48.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.48.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.48.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.49.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.49.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.49.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.50.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.50.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.50.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.51.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.51.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.51.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.52.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.52.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.52.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.53.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.53.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.53.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.54.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.54.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.54.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.55.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.55.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.55.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.56.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.56.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.56.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.57.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.57.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.57.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.58.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.58.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.58.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.59.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.59.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.59.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.60.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.60.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.60.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.61.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.61.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.61.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.62.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.62.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.62.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.63.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.63.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.63.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.64.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.64.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.64.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.65.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.65.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.65.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.66.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.66.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.66.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.67.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.67.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.67.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.68.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.68.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.68.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.69.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.69.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.69.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.70.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.70.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.70.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.71.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.71.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.71.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.72.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.72.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.72.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.73.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.73.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.73.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.74.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.74.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.74.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.75.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.75.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.75.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.76.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.76.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.76.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.77.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.77.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.77.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.78.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.78.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.78.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.79.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.79.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.79.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.8.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.8.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.8.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.80.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.80.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.80.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.81.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.81.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.81.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.82.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.82.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.82.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.83.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.83.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.83.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.84.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.84.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.84.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.85.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.85.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.85.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.86.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.86.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.86.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.87.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.87.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.87.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.88.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.88.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.88.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.89.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.89.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.89.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.9.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.9.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.9.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.90.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.90.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.90.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.91.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.91.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.91.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.92.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.92.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.92.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.93.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.93.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.93.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.94.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.94.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.94.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.95.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.95.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.95.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.96.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.96.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.96.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.97.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.97.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.97.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.98.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.98.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.98.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.99.w1.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.99.w2.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.experts.99.w3.weight": "model-00019-of-00020.safetensors", "model.layers.60.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.60.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.60.self_attn.k_norm.weight": "model-00019-of-00020.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.60.self_attn.q_norm.weight": "model-00019-of-00020.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.10.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.10.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.10.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.100.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.100.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.100.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.101.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.101.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.101.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.102.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.102.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.102.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.103.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.103.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.103.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.104.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.104.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.104.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.105.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.105.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.105.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.106.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.106.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.106.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.107.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.107.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.107.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.108.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.108.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.108.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.109.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.109.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.109.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.11.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.11.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.11.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.110.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.110.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.110.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.111.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.111.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.111.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.112.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.112.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.112.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.113.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.113.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.113.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.114.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.114.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.114.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.115.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.115.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.115.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.12.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.12.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.12.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.13.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.13.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.13.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.14.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.14.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.14.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.15.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.15.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.15.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.16.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.16.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.16.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.17.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.17.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.17.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.18.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.18.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.18.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.19.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.19.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.19.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.20.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.20.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.20.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.21.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.21.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.21.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.22.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.22.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.22.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.23.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.23.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.23.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.24.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.24.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.24.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.25.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.25.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.25.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.26.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.26.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.26.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.27.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.27.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.27.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.28.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.28.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.28.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.29.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.29.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.29.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.30.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.30.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.30.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.31.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.31.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.31.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.32.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.32.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.32.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.33.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.33.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.33.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.34.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.34.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.34.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.35.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.35.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.35.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.36.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.36.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.36.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.37.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.37.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.37.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.38.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.38.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.38.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.39.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.39.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.39.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.40.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.40.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.40.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.41.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.41.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.41.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.42.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.42.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.42.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.43.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.43.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.43.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.44.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.44.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.44.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.45.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.45.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.45.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.46.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.46.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.46.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.47.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.47.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.47.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.48.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.48.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.48.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.49.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.49.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.49.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.50.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.50.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.50.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.51.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.51.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.51.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.52.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.52.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.52.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.53.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.53.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.53.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.54.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.54.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.54.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.55.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.55.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.55.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.56.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.56.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.56.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.57.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.57.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.57.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.58.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.58.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.58.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.59.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.59.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.59.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.60.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.60.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.60.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.61.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.61.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.61.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.62.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.62.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.62.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.63.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.63.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.63.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.64.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.64.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.64.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.65.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.65.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.65.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.66.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.66.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.66.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.67.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.67.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.67.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.68.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.68.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.68.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.69.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.69.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.69.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.70.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.70.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.70.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.71.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.71.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.71.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.72.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.72.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.72.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.73.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.73.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.73.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.74.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.74.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.74.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.75.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.75.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.75.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.76.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.76.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.76.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.77.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.77.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.77.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.78.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.78.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.78.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.79.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.79.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.79.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.8.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.8.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.8.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.80.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.80.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.80.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.81.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.81.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.81.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.82.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.82.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.82.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.83.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.83.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.83.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.84.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.84.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.84.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.85.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.85.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.85.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.86.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.86.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.86.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.87.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.87.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.87.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.88.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.88.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.88.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.89.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.89.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.89.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.9.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.9.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.9.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.90.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.90.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.90.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.91.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.91.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.91.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.92.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.92.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.92.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.93.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.93.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.93.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.94.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.94.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.94.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.95.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.95.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.95.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.96.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.96.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.96.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.97.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.97.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.97.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.98.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.98.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.98.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.99.w1.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.99.w2.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.experts.99.w3.weight": "model-00019-of-00020.safetensors", "model.layers.61.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.61.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.61.self_attn.k_norm.weight": "model-00019-of-00020.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.61.self_attn.q_norm.weight": "model-00019-of-00020.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.10.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.10.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.10.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.100.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.100.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.100.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.101.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.101.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.101.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.102.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.102.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.102.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.103.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.103.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.103.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.104.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.104.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.104.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.105.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.105.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.105.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.106.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.106.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.106.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.107.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.107.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.107.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.108.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.108.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.108.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.109.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.109.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.109.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.11.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.11.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.11.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.110.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.110.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.110.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.111.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.111.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.111.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.112.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.112.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.112.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.113.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.113.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.113.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.114.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.114.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.114.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.115.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.115.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.115.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.12.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.12.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.12.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.13.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.13.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.13.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.14.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.14.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.14.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.15.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.15.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.15.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.16.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.16.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.16.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.17.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.17.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.17.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.18.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.18.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.18.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.19.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.19.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.19.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.20.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.20.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.20.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.21.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.21.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.21.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.22.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.22.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.22.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.23.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.23.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.23.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.24.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.24.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.24.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.25.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.25.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.25.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.26.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.26.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.26.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.27.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.27.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.27.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.28.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.28.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.28.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.29.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.29.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.29.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.30.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.30.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.30.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.31.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.31.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.31.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.32.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.32.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.32.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.33.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.33.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.33.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.34.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.34.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.34.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.35.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.35.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.35.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.36.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.36.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.36.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.37.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.37.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.37.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.38.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.38.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.38.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.39.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.39.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.39.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.40.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.40.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.40.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.41.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.41.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.41.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.42.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.42.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.42.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.43.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.43.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.43.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.44.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.44.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.44.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.45.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.45.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.45.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.46.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.46.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.46.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.47.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.47.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.47.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.48.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.48.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.48.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.49.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.49.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.49.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.50.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.50.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.50.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.51.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.51.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.51.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.52.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.52.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.52.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.53.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.53.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.53.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.54.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.54.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.54.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.55.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.55.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.55.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.56.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.56.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.56.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.57.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.57.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.57.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.58.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.58.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.58.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.59.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.59.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.59.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.60.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.60.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.60.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.61.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.61.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.61.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.62.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.62.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.62.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.63.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.63.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.63.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.64.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.64.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.64.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.65.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.65.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.65.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.66.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.66.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.66.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.67.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.67.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.67.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.68.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.68.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.68.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.69.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.69.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.69.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.70.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.70.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.70.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.71.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.71.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.71.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.72.w1.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.72.w2.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.72.w3.weight": "model-00019-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.73.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.73.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.73.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.74.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.74.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.74.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.75.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.75.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.75.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.76.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.76.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.76.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.77.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.77.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.77.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.78.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.78.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.78.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.79.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.79.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.79.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.8.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.8.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.8.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.80.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.80.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.80.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.81.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.81.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.81.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.82.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.82.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.82.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.83.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.83.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.83.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.84.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.84.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.84.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.85.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.85.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.85.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.86.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.86.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.86.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.87.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.87.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.87.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.88.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.88.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.88.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.89.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.89.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.89.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.9.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.9.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.9.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.90.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.90.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.90.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.91.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.91.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.91.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.92.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.92.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.92.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.93.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.93.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.93.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.94.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.94.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.94.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.95.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.95.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.95.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.96.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.96.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.96.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.97.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.97.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.97.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.98.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.98.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.98.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.99.w1.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.99.w2.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.99.w3.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.7.input_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.7.self_attn.k_norm.weight": "model-00020-of-00020.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.7.self_attn.q_norm.weight": "model-00020-of-00020.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.10.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.10.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.10.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.100.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.100.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.100.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.101.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.101.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.101.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.102.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.102.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.102.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.103.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.103.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.103.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.104.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.104.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.104.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.105.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.105.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.105.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.106.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.106.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.106.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.107.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.107.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.107.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.108.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.108.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.108.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.109.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.109.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.109.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.11.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.11.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.11.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.110.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.110.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.110.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.111.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.111.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.111.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.112.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.112.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.112.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.113.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.113.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.113.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.114.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.114.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.114.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.115.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.115.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.115.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.12.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.12.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.12.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.13.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.13.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.13.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.14.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.14.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.14.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.15.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.15.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.15.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.16.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.16.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.16.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.17.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.17.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.17.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.18.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.18.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.18.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.19.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.19.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.19.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.20.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.20.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.20.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.21.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.21.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.21.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.22.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.22.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.22.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.23.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.23.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.23.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.24.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.24.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.24.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.25.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.25.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.25.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.26.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.26.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.26.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.27.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.27.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.27.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.28.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.28.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.28.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.29.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.29.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.29.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.30.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.30.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.30.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.31.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.31.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.31.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.32.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.32.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.32.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.33.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.33.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.33.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.34.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.34.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.34.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.35.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.35.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.35.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.36.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.36.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.36.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.37.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.37.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.37.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.38.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.38.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.38.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.39.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.39.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.39.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.40.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.40.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.40.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.41.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.41.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.41.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.42.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.42.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.42.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.43.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.43.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.43.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.44.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.44.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.44.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.45.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.45.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.45.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.46.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.46.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.46.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.47.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.47.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.47.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.48.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.48.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.48.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.49.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.49.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.49.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.50.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.50.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.50.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.51.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.51.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.51.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.52.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.52.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.52.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.53.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.53.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.53.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.54.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.54.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.54.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.55.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.55.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.55.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.56.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.56.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.56.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.57.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.57.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.57.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.58.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.58.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.58.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.59.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.59.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.59.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.60.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.60.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.60.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.61.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.61.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.61.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.62.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.62.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.62.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.63.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.63.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.63.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.64.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.64.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.64.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.65.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.65.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.65.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.66.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.66.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.66.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.67.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.67.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.67.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.68.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.68.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.68.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.69.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.69.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.69.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.70.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.70.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.70.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.71.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.71.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.71.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.72.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.72.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.72.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.73.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.73.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.73.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.74.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.74.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.74.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.75.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.75.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.75.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.76.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.76.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.76.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.77.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.77.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.77.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.78.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.78.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.78.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.79.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.79.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.79.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.8.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.8.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.8.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.80.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.80.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.80.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.81.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.81.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.81.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.82.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.82.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.82.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.83.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.83.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.83.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.84.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.84.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.84.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.85.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.85.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.85.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.86.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.86.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.86.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.87.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.87.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.87.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.88.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.88.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.88.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.89.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.89.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.89.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.9.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.9.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.9.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.90.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.90.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.90.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.91.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.91.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.91.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.92.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.92.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.92.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.93.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.93.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.93.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.94.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.94.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.94.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.95.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.95.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.95.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.96.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.96.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.96.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.97.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.97.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.97.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.98.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.98.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.98.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.99.w1.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.99.w2.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.99.w3.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.8.input_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.k_norm.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.q_norm.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.10.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.10.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.10.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.100.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.100.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.100.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.101.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.101.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.101.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.102.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.102.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.102.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.103.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.103.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.103.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.104.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.104.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.104.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.105.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.105.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.105.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.106.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.106.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.106.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.107.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.107.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.107.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.108.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.108.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.108.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.109.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.109.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.109.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.11.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.11.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.11.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.110.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.110.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.110.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.111.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.111.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.111.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.112.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.112.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.112.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.113.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.113.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.113.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.114.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.114.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.114.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.115.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.115.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.115.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.12.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.12.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.12.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.13.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.13.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.13.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.14.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.14.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.14.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.15.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.15.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.15.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.16.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.16.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.16.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.17.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.17.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.17.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.18.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.18.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.18.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.19.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.19.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.19.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.20.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.20.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.20.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.21.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.21.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.21.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.22.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.22.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.22.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.23.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.23.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.23.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.24.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.24.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.24.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.25.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.25.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.25.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.26.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.26.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.26.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.27.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.27.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.27.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.28.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.28.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.28.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.29.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.29.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.29.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.30.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.30.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.30.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.31.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.31.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.31.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.32.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.32.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.32.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.33.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.33.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.33.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.34.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.34.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.34.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.35.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.35.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.35.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.36.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.36.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.36.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.37.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.37.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.37.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.38.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.38.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.38.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.39.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.39.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.39.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.40.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.40.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.40.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.41.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.41.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.41.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.42.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.42.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.42.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.43.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.43.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.43.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.44.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.44.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.44.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.45.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.45.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.45.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.46.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.46.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.46.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.47.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.47.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.47.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.48.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.48.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.48.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.49.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.49.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.49.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.50.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.50.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.50.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.51.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.51.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.51.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.52.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.52.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.52.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.53.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.53.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.53.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.54.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.54.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.54.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.55.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.55.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.55.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.56.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.56.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.56.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.57.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.57.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.57.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.58.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.58.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.58.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.59.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.59.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.59.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.60.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.60.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.60.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.61.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.61.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.61.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.62.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.62.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.62.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.63.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.63.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.63.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.64.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.64.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.64.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.65.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.65.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.65.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.66.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.66.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.66.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.67.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.67.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.67.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.68.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.68.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.68.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.69.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.69.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.69.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.70.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.70.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.70.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.71.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.71.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.71.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.72.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.72.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.72.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.73.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.73.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.73.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.74.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.74.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.74.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.75.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.75.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.75.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.76.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.76.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.76.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.77.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.77.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.77.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.78.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.78.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.78.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.79.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.79.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.79.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.8.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.8.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.8.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.80.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.80.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.80.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.81.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.81.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.81.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.82.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.82.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.82.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.83.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.83.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.83.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.84.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.84.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.84.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.85.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.85.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.85.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.86.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.86.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.86.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.87.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.87.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.87.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.88.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.88.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.88.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.89.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.89.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.89.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.9.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.9.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.9.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.90.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.90.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.90.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.91.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.91.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.91.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.92.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.92.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.92.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.93.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.93.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.93.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.94.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.94.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.94.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.95.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.95.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.95.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.96.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.96.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.96.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.97.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.97.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.97.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.98.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.98.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.98.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.99.w1.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.99.w2.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.99.w3.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.9.input_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.k_norm.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.q_norm.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.norm.weight": "model-00020-of-00020.safetensors"}} \ No newline at end of file