Added bf16 tensors

config.json

@@ -28,7 +28,7 @@
   "rope_theta": 1500000.0,
   "router_aux_loss_coef": 0.0,
   "tie_word_embeddings": true,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 49155

model-00002-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8736d26aee8bcaa1cf41942aa23edaef11a99c4f4715fee7b7b23180beec9674
-size 415520528

model-00001-of-00002.safetensors → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a41fd0fd2ab25fe0553b47b8777f49ad68866d2878ba374bf8cc3b0ed6421490
-size 4923019144
+oid sha256:ac02591061f1344027a7e7b11dbb4143f75f166c47dc09b742f5de3ab1dde1d1
+size 2669283096

model.safetensors.index.json

@@ -1,225 +0,0 @@
-{
-  "metadata": {
-    "total_size": 5338513408
-  },
-  "weight_map": {
-    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.block_sparse_moe.input_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.block_sparse_moe.output_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.3.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.block_sparse_moe.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.norm.weight": "model-00002-of-00002.safetensors"
-  }
-}