diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json" --- "a/model.safetensors.index.json" +++ "b/model.safetensors.index.json" @@ -1,7 +1,7 @@ { "metadata": { - "total_parameters": 4605856128, - "total_size": 16686185472 + "total_parameters": 5306567040, + "total_size": 18087607296 }, "weight_map": { "lm_head.weight": "model-00004-of-00004.safetensors", @@ -4682,7 +4682,7 @@ "model.layers.11.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.experts.0.down_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.0.down_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.0.down_proj.weight_shape": "model-00001-of-00004.safetensors", @@ -4710,96 +4710,96 @@ "model.layers.12.mlp.experts.10.up_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.10.up_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.10.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.100.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.100.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.100.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.100.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.100.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.100.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.100.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.100.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.100.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.101.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.101.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.101.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.101.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.101.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.101.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.101.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.101.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.101.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.102.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.102.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.102.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.102.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.102.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.102.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.102.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.102.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.102.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.103.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.103.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.103.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.103.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.103.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.103.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.103.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.103.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.103.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.104.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.104.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.104.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.104.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.104.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.104.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.104.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.104.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.104.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.105.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.105.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.105.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.105.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.105.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.105.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.105.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.105.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.105.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.106.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.106.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.106.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.106.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.106.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.106.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.106.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.106.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.106.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.107.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.107.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.107.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.107.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.107.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.107.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.107.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.107.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.107.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.108.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.108.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.108.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.108.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.108.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.108.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.108.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.108.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.108.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.109.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.109.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.109.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.109.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.109.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.109.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.109.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.109.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.109.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.12.mlp.experts.11.down_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.11.down_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.11.down_proj.weight_shape": "model-00001-of-00004.safetensors", @@ -4809,96 +4809,96 @@ "model.layers.12.mlp.experts.11.up_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.11.up_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.11.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.110.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.110.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.110.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.110.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.110.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.110.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.110.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.110.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.110.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.111.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.111.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.111.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.111.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.111.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.111.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.111.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.111.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.111.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.112.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.112.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.112.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.112.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.112.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.112.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.112.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.112.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.112.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.113.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.113.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.113.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.113.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.113.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.113.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.113.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.113.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.113.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.114.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.114.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.114.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.114.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.114.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.114.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.114.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.114.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.114.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.115.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.115.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.115.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.115.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.115.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.115.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.115.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.115.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.115.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.116.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.116.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.116.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.116.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.116.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.116.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.116.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.116.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.116.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.117.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.117.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.117.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.117.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.117.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.117.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.117.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.117.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.117.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.118.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.118.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.118.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.118.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.118.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.118.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.118.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.118.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.118.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.119.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.119.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.119.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.119.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.119.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.119.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.119.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.119.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.119.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.12.mlp.experts.12.down_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.12.down_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.12.down_proj.weight_shape": "model-00001-of-00004.safetensors", @@ -4908,78 +4908,78 @@ "model.layers.12.mlp.experts.12.up_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.12.up_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.12.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.120.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.120.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.120.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.120.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.120.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.120.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.120.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.120.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.120.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.121.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.121.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.121.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.121.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.121.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.121.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.121.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.121.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.121.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.122.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.122.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.122.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.122.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.122.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.122.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.122.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.122.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.122.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.123.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.123.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.123.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.123.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.123.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.123.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.123.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.123.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.123.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.124.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.124.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.124.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.124.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.124.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.124.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.124.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.124.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.124.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.125.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.125.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.125.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.125.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.125.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.125.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.125.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.125.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.125.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.126.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.126.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.126.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.126.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.126.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.126.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.126.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.126.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.126.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.127.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.127.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.127.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.127.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.127.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.127.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.127.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.127.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.127.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.12.mlp.experts.13.down_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.13.down_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.13.down_proj.weight_shape": "model-00001-of-00004.safetensors", @@ -5421,8 +5421,8 @@ "model.layers.12.mlp.experts.57.up_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.57.up_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.57.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.58.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.58.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.12.mlp.experts.58.down_proj.weight_shape": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.58.gate_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.58.gate_proj.weight_scale": "model-00001-of-00004.safetensors", @@ -5430,15 +5430,15 @@ "model.layers.12.mlp.experts.58.up_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.58.up_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.58.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.59.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.59.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.59.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.59.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.59.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.59.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.59.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.59.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.59.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.12.mlp.experts.6.down_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.6.down_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.6.down_proj.weight_shape": "model-00001-of-00004.safetensors", @@ -5448,96 +5448,96 @@ "model.layers.12.mlp.experts.6.up_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.6.up_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.6.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.60.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.60.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.60.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.60.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.60.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.60.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.60.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.60.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.60.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.61.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.61.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.61.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.61.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.61.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.61.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.61.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.61.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.61.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.62.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.62.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.62.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.62.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.62.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.62.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.62.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.62.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.62.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.63.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.63.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.63.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.63.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.63.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.63.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.63.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.63.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.63.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.64.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.64.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.64.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.64.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.64.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.64.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.64.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.64.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.64.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.65.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.65.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.65.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.65.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.65.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.65.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.65.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.65.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.65.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.66.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.66.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.66.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.66.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.66.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.66.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.66.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.66.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.66.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.67.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.67.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.67.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.67.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.67.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.67.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.67.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.67.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.67.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.68.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.68.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.68.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.68.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.68.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.68.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.68.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.68.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.68.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.69.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.69.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.69.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.69.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.69.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.69.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.69.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.69.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.69.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.12.mlp.experts.7.down_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.7.down_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.7.down_proj.weight_shape": "model-00001-of-00004.safetensors", @@ -5547,96 +5547,96 @@ "model.layers.12.mlp.experts.7.up_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.7.up_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.7.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.70.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.70.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.70.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.70.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.70.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.70.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.70.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.70.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.70.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.71.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.71.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.71.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.71.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.71.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.71.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.71.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.71.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.71.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.72.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.72.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.72.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.72.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.72.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.72.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.72.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.72.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.72.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.73.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.73.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.73.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.73.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.73.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.73.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.73.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.73.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.73.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.74.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.74.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.74.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.74.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.74.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.74.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.74.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.74.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.74.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.75.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.75.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.75.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.75.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.75.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.75.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.75.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.75.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.75.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.76.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.76.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.76.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.76.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.76.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.76.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.76.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.76.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.76.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.77.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.77.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.77.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.77.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.77.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.77.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.77.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.77.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.77.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.78.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.78.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.78.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.78.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.78.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.78.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.78.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.78.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.78.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.79.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.79.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.79.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.79.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.79.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.79.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.79.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.79.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.79.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.12.mlp.experts.8.down_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.8.down_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.8.down_proj.weight_shape": "model-00001-of-00004.safetensors", @@ -5646,96 +5646,96 @@ "model.layers.12.mlp.experts.8.up_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.8.up_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.8.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.80.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.80.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.80.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.80.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.80.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.80.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.80.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.80.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.80.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.81.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.81.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.81.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.81.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.81.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.81.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.81.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.81.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.81.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.82.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.82.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.82.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.82.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.82.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.82.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.82.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.82.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.82.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.83.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.83.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.83.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.83.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.83.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.83.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.83.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.83.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.83.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.84.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.84.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.84.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.84.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.84.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.84.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.84.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.84.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.84.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.85.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.85.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.85.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.85.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.85.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.85.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.85.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.85.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.85.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.86.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.86.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.86.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.86.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.86.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.86.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.86.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.86.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.86.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.87.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.87.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.87.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.87.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.87.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.87.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.87.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.87.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.87.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.88.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.88.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.88.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.88.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.88.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.88.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.88.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.88.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.88.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.89.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.89.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.89.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.89.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.89.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.89.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.89.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.89.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.89.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.12.mlp.experts.9.down_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.9.down_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.9.down_proj.weight_shape": "model-00001-of-00004.safetensors", @@ -5745,98 +5745,98 @@ "model.layers.12.mlp.experts.9.up_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.9.up_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.mlp.experts.9.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.90.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.90.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.90.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.90.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.90.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.90.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.90.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.90.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.90.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.91.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.91.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.91.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.91.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.91.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.91.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.91.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.91.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.91.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.92.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.92.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.92.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.92.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.92.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.92.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.92.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.92.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.92.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.93.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.93.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.93.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.93.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.93.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.93.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.93.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.93.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.93.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.94.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.94.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.94.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.94.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.94.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.94.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.94.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.94.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.94.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.95.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.95.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.95.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.95.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.95.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.95.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.95.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.95.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.95.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.96.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.96.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.96.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.96.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.96.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.96.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.96.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.96.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.96.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.97.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.97.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.97.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.97.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.97.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.97.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.97.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.97.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.97.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.98.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.98.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.98.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.98.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.98.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.98.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.98.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.98.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.98.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.99.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.99.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.99.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.99.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.99.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.99.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.99.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.99.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.12.mlp.experts.99.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.12.mlp.gate.weight": "model-00001-of-00004.safetensors", - "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", @@ -5852,33 +5852,33 @@ "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.13.mlp.experts.0.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.0.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.0.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.0.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.0.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.0.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.0.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.0.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.0.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.1.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.1.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.1.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.1.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.1.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.1.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.1.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.1.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.1.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.10.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.10.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.10.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.10.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.10.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.10.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.10.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.10.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.10.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.100.down_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.100.down_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.100.down_proj.weight_shape": "model-00002-of-00004.safetensors", @@ -5969,15 +5969,15 @@ "model.layers.13.mlp.experts.109.up_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.109.up_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.109.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.13.mlp.experts.11.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.11.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.11.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.11.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.11.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.11.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.11.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.11.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.11.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.110.down_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.110.down_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.110.down_proj.weight_shape": "model-00002-of-00004.safetensors", @@ -6068,15 +6068,15 @@ "model.layers.13.mlp.experts.119.up_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.119.up_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.119.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.13.mlp.experts.12.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.12.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.12.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.12.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.12.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.12.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.12.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.12.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.12.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.120.down_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.120.down_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.120.down_proj.weight_shape": "model-00002-of-00004.safetensors", @@ -6149,633 +6149,633 @@ "model.layers.13.mlp.experts.127.up_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.127.up_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.127.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.13.mlp.experts.13.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.13.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.13.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.13.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.13.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.13.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.13.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.13.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.13.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.14.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.14.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.14.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.14.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.14.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.14.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.14.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.14.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.14.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.15.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.15.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.15.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.15.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.15.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.15.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.15.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.15.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.15.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.16.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.16.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.16.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.16.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.16.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.16.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.16.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.16.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.16.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.17.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.17.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.17.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.17.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.17.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.17.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.17.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.17.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.17.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.18.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.18.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.18.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.18.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.18.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.18.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.18.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.18.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.18.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.19.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.19.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.19.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.19.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.19.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.19.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.19.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.19.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.19.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.2.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.2.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.2.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.2.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.2.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.2.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.2.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.2.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.2.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.20.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.20.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.20.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.20.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.20.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.20.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.20.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.20.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.20.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.21.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.21.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.21.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.21.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.21.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.21.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.21.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.21.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.21.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.22.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.22.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.22.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.22.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.22.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.22.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.22.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.22.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.22.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.23.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.23.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.23.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.23.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.23.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.23.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.23.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.23.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.23.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.24.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.24.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.24.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.24.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.24.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.24.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.24.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.24.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.24.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.25.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.25.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.25.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.25.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.25.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.25.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.25.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.25.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.25.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.26.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.26.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.26.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.26.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.26.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.26.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.26.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.26.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.26.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.27.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.27.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.27.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.27.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.27.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.27.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.27.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.27.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.27.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.28.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.28.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.28.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.28.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.28.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.28.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.28.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.28.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.28.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.29.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.29.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.29.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.29.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.29.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.29.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.29.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.29.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.29.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.3.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.3.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.3.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.3.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.3.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.3.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.3.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.3.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.3.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.30.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.30.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.30.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.30.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.30.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.30.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.30.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.30.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.30.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.31.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.31.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.31.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.31.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.31.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.31.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.31.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.31.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.31.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.32.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.32.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.32.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.32.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.32.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.32.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.32.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.32.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.32.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.33.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.33.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.33.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.33.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.33.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.33.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.33.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.33.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.33.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.34.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.34.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.34.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.34.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.34.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.34.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.34.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.34.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.34.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.35.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.35.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.35.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.35.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.35.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.35.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.35.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.35.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.35.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.36.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.36.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.36.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.36.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.36.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.36.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.36.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.36.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.36.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.37.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.37.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.37.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.37.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.37.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.37.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.37.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.37.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.37.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.38.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.38.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.38.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.38.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.38.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.38.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.38.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.38.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.38.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.39.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.39.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.39.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.39.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.39.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.39.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.39.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.39.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.39.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.4.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.4.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.4.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.4.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.4.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.4.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.4.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.4.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.4.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.40.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.40.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.40.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.40.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.40.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.40.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.40.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.40.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.40.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.41.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.41.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.41.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.41.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.41.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.41.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.41.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.41.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.41.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.42.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.42.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.42.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.42.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.42.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.42.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.42.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.42.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.42.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.43.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.43.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.43.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.43.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.43.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.43.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.43.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.43.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.43.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.44.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.44.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.44.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.44.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.44.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.44.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.44.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.44.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.44.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.45.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.45.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.45.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.45.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.45.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.45.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.45.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.45.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.45.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.46.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.46.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.46.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.46.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.46.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.46.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.46.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.46.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.46.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.47.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.47.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.47.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.47.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.47.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.47.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.47.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.47.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.47.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.48.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.48.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.48.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.48.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.48.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.48.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.48.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.48.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.48.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.49.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.49.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.49.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.49.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.49.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.49.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.49.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.49.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.49.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.5.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.5.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.5.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.5.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.5.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.5.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.5.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.5.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.5.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.50.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.50.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.50.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.50.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.50.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.50.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.50.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.50.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.50.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.51.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.51.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.51.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.51.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.51.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.51.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.51.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.51.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.51.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.52.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.52.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.52.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.52.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.52.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.52.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.52.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.52.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.52.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.53.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.53.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.53.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.53.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.53.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.53.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.53.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.53.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.53.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.54.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.54.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.54.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.54.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.54.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.54.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.54.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.54.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.54.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.55.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.55.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.55.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.55.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.55.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.55.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.55.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.55.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.55.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.56.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.56.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.56.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.56.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.56.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.56.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.56.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.56.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.56.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.57.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.57.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.57.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.57.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.57.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.57.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.57.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.57.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.57.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.58.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.58.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.58.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.58.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.58.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.58.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.58.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.58.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.58.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.59.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.59.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.59.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.59.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.59.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.59.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.59.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.59.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.59.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.6.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.6.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.6.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.6.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.6.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.6.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.6.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.6.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.6.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.60.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.60.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.60.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.60.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.60.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.60.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.60.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.60.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.60.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.61.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.61.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.61.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.61.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.61.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.61.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.61.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.61.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.61.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.62.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.62.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.62.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.62.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.62.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.62.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.62.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.62.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.62.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.63.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.63.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.63.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.63.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.63.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.63.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.63.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.63.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.63.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.64.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.64.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.64.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.64.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.64.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.64.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.64.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.64.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.64.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.65.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.65.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.65.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.65.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.65.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.65.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.65.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.65.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.65.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.66.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.66.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.66.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.66.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.66.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.66.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.66.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.66.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.66.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.67.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.67.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.67.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.67.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.67.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.67.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.67.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.67.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.67.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.68.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.68.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.68.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.68.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.68.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.68.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.68.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.68.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.68.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.69.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.69.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.69.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.69.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.69.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.69.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.69.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.69.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.69.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.7.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.7.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.7.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.7.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.7.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.7.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.7.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.7.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.7.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.70.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.70.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.70.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.70.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.70.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.70.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.70.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.70.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.70.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.71.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.71.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.71.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.71.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.71.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.71.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.71.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.71.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.71.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.72.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.72.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.72.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.72.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.72.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.72.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.72.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.72.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.72.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.73.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.73.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.73.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.73.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.73.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.73.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.73.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.73.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.73.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.74.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.74.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.74.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.74.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.74.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.74.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.74.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.74.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.74.up_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.75.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.75.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.75.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.75.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.75.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.75.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.75.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.75.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.75.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.76.down_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.76.down_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.76.down_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.76.gate_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.76.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.13.mlp.experts.76.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.experts.76.gate_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.76.up_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.76.up_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.76.up_proj.weight_shape": "model-00002-of-00004.safetensors", @@ -6806,15 +6806,15 @@ "model.layers.13.mlp.experts.79.up_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.79.up_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.79.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.13.mlp.experts.8.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.8.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.8.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.8.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.8.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.8.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.8.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.8.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.8.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.80.down_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.80.down_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.80.down_proj.weight_shape": "model-00002-of-00004.safetensors", @@ -6905,15 +6905,15 @@ "model.layers.13.mlp.experts.89.up_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.89.up_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.89.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.13.mlp.experts.9.down_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.9.down_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.9.down_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.9.gate_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.9.gate_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.9.gate_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.9.up_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.9.up_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.mlp.experts.9.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.90.down_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.90.down_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.90.down_proj.weight_shape": "model-00002-of-00004.safetensors", @@ -7004,22 +7004,22 @@ "model.layers.13.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.13.mlp.experts.99.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.13.mlp.gate.weight": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", - "model.layers.13.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", - "model.layers.13.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.13.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", - "model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", - "model.layers.13.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.experts.0.down_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.14.mlp.experts.0.down_proj.weight_scale": "model-00002-of-00004.safetensors", @@ -22217,7 +22217,7 @@ "model.layers.25.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.experts.0.down_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.0.down_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.0.down_proj.weight_shape": "model-00002-of-00004.safetensors", @@ -22245,96 +22245,96 @@ "model.layers.26.mlp.experts.10.up_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.10.up_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.10.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.100.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.100.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.100.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.100.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.100.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.100.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.100.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.100.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.100.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.101.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.101.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.101.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.101.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.101.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.101.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.101.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.101.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.101.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.102.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.102.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.102.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.102.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.102.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.102.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.102.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.102.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.102.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.103.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.103.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.103.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.103.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.103.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.103.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.103.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.103.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.103.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.104.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.104.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.104.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.104.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.104.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.104.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.104.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.104.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.104.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.105.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.105.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.105.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.105.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.105.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.105.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.105.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.105.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.105.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.106.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.106.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.106.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.106.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.106.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.106.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.106.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.106.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.106.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.107.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.107.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.107.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.107.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.107.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.107.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.107.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.107.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.107.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.108.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.108.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.108.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.108.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.108.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.108.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.108.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.108.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.108.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.109.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.109.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.109.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.109.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.109.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.109.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.109.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.109.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.109.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.26.mlp.experts.11.down_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.11.down_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.11.down_proj.weight_shape": "model-00002-of-00004.safetensors", @@ -22344,96 +22344,96 @@ "model.layers.26.mlp.experts.11.up_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.11.up_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.11.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.110.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.110.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.110.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.110.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.110.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.110.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.110.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.110.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.110.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.111.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.111.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.111.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.111.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.111.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.111.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.111.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.111.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.111.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.112.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.112.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.112.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.112.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.112.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.112.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.112.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.112.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.112.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.113.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.113.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.113.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.113.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.113.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.113.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.113.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.113.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.113.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.114.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.114.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.114.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.114.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.114.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.114.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.114.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.114.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.114.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.115.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.115.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.115.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.115.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.115.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.115.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.115.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.115.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.115.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.116.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.116.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.116.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.116.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.116.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.116.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.116.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.116.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.116.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.117.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.117.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.117.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.117.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.117.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.117.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.117.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.117.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.117.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.118.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.118.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.118.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.118.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.118.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.118.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.118.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.118.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.118.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.119.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.119.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.119.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.119.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.119.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.119.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.119.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.119.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.119.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.26.mlp.experts.12.down_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.12.down_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.12.down_proj.weight_shape": "model-00002-of-00004.safetensors", @@ -22443,78 +22443,78 @@ "model.layers.26.mlp.experts.12.up_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.12.up_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.12.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.120.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.120.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.120.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.120.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.120.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.120.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.120.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.120.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.120.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.121.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.121.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.121.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.121.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.121.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.121.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.121.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.121.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.121.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.122.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.122.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.122.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.122.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.122.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.122.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.122.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.122.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.122.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.123.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.123.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.123.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.123.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.123.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.123.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.123.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.123.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.123.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.124.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.124.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.124.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.124.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.124.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.124.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.124.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.124.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.124.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.125.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.125.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.125.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.125.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.125.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.125.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.125.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.125.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.125.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.126.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.126.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.126.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.126.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.126.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.126.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.126.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.126.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.126.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.127.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.127.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.127.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.127.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.127.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.127.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.127.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.127.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.127.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.26.mlp.experts.13.down_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.13.down_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.13.down_proj.weight_shape": "model-00002-of-00004.safetensors", @@ -23289,89 +23289,89 @@ "model.layers.26.mlp.experts.90.up_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.90.up_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.90.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.91.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.91.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.91.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.26.mlp.experts.91.gate_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.91.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.26.mlp.experts.91.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.91.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.91.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.26.mlp.experts.91.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.92.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.92.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.92.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.92.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.92.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.92.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.92.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.92.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.92.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.93.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.93.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.93.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.93.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.93.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.93.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.93.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.93.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.93.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.94.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.94.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.94.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.94.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.94.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.94.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.94.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.94.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.94.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.95.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.95.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.95.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.95.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.95.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.95.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.95.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.95.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.95.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.96.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.96.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.96.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.96.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.96.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.96.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.96.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.96.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.96.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.97.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.97.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.97.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.97.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.97.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.97.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.97.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.97.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.97.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.98.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.98.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.98.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.98.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.98.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.98.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.98.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.98.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.98.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.99.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.99.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.99.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.99.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.99.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.99.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.experts.99.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.26.mlp.gate.weight": "model-00002-of-00004.safetensors", - "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", @@ -23386,2372 +23386,2372 @@ "model.layers.26.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.0.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.0.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.0.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.0.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.0.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.0.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.0.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.0.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.0.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.1.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.1.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.1.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.1.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.1.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.1.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.1.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.1.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.1.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.10.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.10.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.10.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.10.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.10.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.10.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.10.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.10.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.10.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.100.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.100.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.100.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.100.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.100.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.100.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.100.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.100.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.100.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.101.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.101.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.101.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.101.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.101.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.101.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.101.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.101.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.101.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.102.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.102.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.102.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.102.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.102.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.102.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.102.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.102.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.102.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.103.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.103.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.103.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.103.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.103.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.103.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.103.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.103.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.103.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.104.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.104.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.104.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.104.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.104.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.104.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.104.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.104.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.104.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.105.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.105.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.105.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.105.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.105.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.105.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.105.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.105.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.105.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.106.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.106.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.106.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.106.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.106.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.106.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.106.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.106.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.106.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.107.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.107.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.107.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.107.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.107.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.107.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.107.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.107.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.107.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.108.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.108.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.108.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.108.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.108.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.108.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.108.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.108.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.108.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.109.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.109.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.109.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.109.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.109.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.109.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.109.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.109.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.109.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.11.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.11.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.11.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.11.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.11.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.11.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.11.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.11.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.11.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.110.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.110.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.110.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.110.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.110.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.110.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.110.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.110.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.110.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.111.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.111.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.111.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.111.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.111.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.111.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.111.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.111.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.111.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.112.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.112.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.112.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.112.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.112.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.112.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.112.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.112.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.112.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.113.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.113.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.113.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.113.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.113.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.113.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.113.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.113.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.113.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.114.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.114.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.114.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.114.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.114.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.114.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.114.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.114.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.114.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.115.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.115.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.115.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.115.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.115.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.115.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.115.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.115.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.115.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.116.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.116.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.116.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.116.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.116.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.116.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.116.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.116.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.116.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.117.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.117.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.117.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.117.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.117.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.117.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.117.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.117.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.117.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.118.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.118.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.118.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.118.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.118.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.118.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.118.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.118.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.118.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.119.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.119.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.119.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.119.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.119.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.119.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.119.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.119.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.119.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.12.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.12.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.12.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.12.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.12.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.12.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.12.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.12.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.12.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.120.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.120.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.120.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.120.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.120.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.120.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.120.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.120.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.120.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.121.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.121.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.121.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.121.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.121.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.121.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.121.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.121.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.121.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.122.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.122.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.122.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.122.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.122.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.122.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.122.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.122.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.122.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.123.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.123.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.123.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.123.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.123.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.123.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.123.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.123.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.123.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.124.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.124.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.124.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.124.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.124.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.124.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.124.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.124.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.124.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.125.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.125.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.125.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.125.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.125.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.125.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.125.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.125.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.125.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.126.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.126.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.126.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.126.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.126.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.126.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.126.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.126.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.126.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.127.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.127.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.127.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.127.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.127.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.127.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.127.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.127.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.127.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.13.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.13.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.13.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.13.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.13.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.13.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.13.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.13.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.13.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.14.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.14.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.14.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.14.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.14.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.14.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.14.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.14.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.14.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.15.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.15.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.15.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.15.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.15.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.15.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.15.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.15.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.15.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.16.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.16.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.16.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.16.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.16.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.16.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.16.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.16.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.16.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.17.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.17.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.17.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.17.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.17.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.17.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.17.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.17.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.17.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.18.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.18.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.18.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.18.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.18.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.18.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.18.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.18.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.18.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.19.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.19.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.19.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.19.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.19.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.19.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.19.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.19.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.19.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.2.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.2.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.2.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.2.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.2.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.2.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.2.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.2.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.2.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.20.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.20.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.20.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.20.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.20.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.20.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.20.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.20.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.20.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.21.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.21.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.21.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.21.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.21.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.21.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.21.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.21.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.21.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.22.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.22.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.22.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.22.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.22.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.22.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.22.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.22.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.22.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.23.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.23.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.23.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.23.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.23.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.23.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.23.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.23.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.23.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.24.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.24.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.24.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.24.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.24.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.24.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.24.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.24.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.24.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.25.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.25.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.25.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.25.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.25.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.25.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.25.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.25.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.25.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.26.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.26.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.26.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.26.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.26.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.26.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.26.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.26.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.26.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.27.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.27.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.27.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.27.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.27.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.27.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.27.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.27.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.27.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.28.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.28.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.28.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.28.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.28.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.28.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.28.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.28.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.28.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.29.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.29.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.29.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.29.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.29.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.29.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.29.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.29.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.29.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.3.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.3.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.3.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.3.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.3.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.3.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.3.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.3.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.3.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.30.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.30.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.30.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.30.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.30.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.30.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.30.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.30.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.30.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.31.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.31.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.31.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.31.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.31.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.31.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.31.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.31.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.31.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.32.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.32.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.32.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.32.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.32.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.32.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.32.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.32.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.32.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.33.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.33.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.33.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.33.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.33.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.33.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.33.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.33.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.33.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.34.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.34.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.34.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.34.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.34.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.34.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.34.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.34.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.34.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.35.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.35.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.35.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.35.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.35.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.35.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.35.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.35.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.35.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.36.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.36.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.36.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.36.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.36.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.36.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.36.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.36.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.36.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.37.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.37.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.37.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.37.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.37.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.37.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.37.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.37.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.37.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.38.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.38.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.38.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.38.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.38.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.38.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.38.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.38.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.38.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.39.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.39.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.39.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.39.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.39.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.39.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.39.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.39.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.39.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.4.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.4.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.4.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.4.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.4.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.4.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.4.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.4.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.4.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.40.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.40.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.40.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.40.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.40.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.40.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.40.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.40.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.40.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.41.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.41.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.41.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.41.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.41.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.41.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.41.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.41.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.41.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.42.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.42.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.42.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.42.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.42.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.42.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.42.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.42.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.42.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.43.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.43.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.43.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.43.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.43.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.43.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.43.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.43.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.43.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.44.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.44.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.44.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.44.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.44.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.44.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.44.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.44.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.44.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.45.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.45.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.45.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.45.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.45.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.45.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.45.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.45.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.45.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.46.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.46.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.46.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.46.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.46.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.46.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.46.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.46.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.46.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.47.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.47.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.47.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.47.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.47.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.47.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.47.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.47.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.47.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.48.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.48.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.48.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.48.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.48.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.48.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.48.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.48.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.48.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.49.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.49.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.49.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.49.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.49.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.49.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.49.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.49.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.49.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.5.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.5.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.5.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.5.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.5.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.5.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.5.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.5.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.5.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.50.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.50.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.50.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.50.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.50.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.50.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.50.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.50.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.50.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.51.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.51.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.51.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.51.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.51.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.51.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.51.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.51.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.51.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.52.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.52.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.52.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.52.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.52.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.52.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.52.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.52.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.52.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.53.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.53.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.53.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.53.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.53.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.53.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.53.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.53.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.53.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.54.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.54.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.54.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.54.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.54.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.54.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.54.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.54.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.54.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.55.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.55.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.55.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.55.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.55.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.55.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.55.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.55.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.55.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.56.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.56.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.56.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.56.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.56.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.56.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.56.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.56.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.56.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.57.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.57.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.57.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.57.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.57.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.57.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.57.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.57.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.57.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.58.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.58.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.58.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.58.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.58.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.58.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.58.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.58.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.58.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.59.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.59.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.59.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.59.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.59.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.59.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.59.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.59.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.59.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.6.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.6.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.6.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.6.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.6.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.6.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.6.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.6.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.6.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.60.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.60.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.60.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.60.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.60.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.60.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.60.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.60.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.60.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.61.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.61.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.61.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.61.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.61.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.61.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.61.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.61.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.61.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.62.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.62.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.62.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.62.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.62.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.62.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.62.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.62.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.62.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.63.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.63.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.63.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.63.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.63.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.63.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.63.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.63.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.63.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.64.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.64.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.64.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.64.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.64.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.64.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.64.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.64.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.64.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.65.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.65.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.65.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.65.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.65.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.65.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.65.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.65.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.65.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.66.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.66.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.66.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.66.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.66.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.66.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.66.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.66.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.66.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.67.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.67.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.67.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.67.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.67.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.67.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.67.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.67.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.67.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.68.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.68.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.68.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.68.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.68.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.68.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.68.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.68.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.68.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.69.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.69.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.69.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.69.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.69.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.69.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.69.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.69.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.69.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.7.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.7.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.7.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.7.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.7.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.7.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.7.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.7.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.7.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.70.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.70.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.70.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.70.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.70.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.70.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.70.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.70.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.70.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.71.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.71.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.71.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.71.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.71.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.71.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.71.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.71.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.71.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.72.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.72.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.72.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.72.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.72.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.72.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.72.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.72.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.72.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.73.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.73.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.73.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.73.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.73.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.73.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.73.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.73.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.73.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.74.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.74.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.74.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.74.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.74.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.74.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.74.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.74.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.74.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.75.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.75.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.75.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.75.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.75.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.75.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.75.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.75.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.75.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.76.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.76.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.76.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.76.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.76.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.76.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.76.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.76.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.76.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.77.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.77.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.77.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.77.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.77.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.77.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.77.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.77.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.77.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.78.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.78.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.78.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.78.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.78.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.78.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.78.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.78.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.78.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.79.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.79.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.79.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.79.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.79.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.79.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.79.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.79.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.79.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.8.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.8.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.8.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.8.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.8.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.8.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.8.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.8.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.8.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.80.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.80.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.80.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.80.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.80.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.80.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.80.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.80.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.80.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.81.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.81.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.81.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.81.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.81.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.81.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.81.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.81.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.81.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.82.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.82.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.82.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.82.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.82.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.82.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.82.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.82.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.82.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.83.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.83.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.83.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.83.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.83.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.83.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.83.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.83.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.83.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.84.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.84.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.84.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.84.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.84.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.84.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.84.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.84.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.84.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.85.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.85.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.85.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.85.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.85.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.85.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.85.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.85.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.85.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.86.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.86.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.86.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.86.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.86.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.86.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.86.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.86.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.86.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.87.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.87.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.87.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.87.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.87.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.87.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.87.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.87.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.87.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.88.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.88.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.88.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.88.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.88.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.88.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.88.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.88.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.88.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.89.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.89.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.89.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.89.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.89.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.89.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.89.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.89.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.89.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.9.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.9.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.9.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.9.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.9.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.9.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.9.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.9.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.9.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.90.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.90.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.90.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.90.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.90.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.90.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.90.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.90.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.90.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.91.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.91.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.91.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.91.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.91.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.91.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.91.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.91.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.91.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.92.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.92.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.92.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.92.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.92.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.92.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.92.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.92.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.92.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.93.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.93.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.93.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.93.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.93.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.93.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.93.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.93.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.93.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.94.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.94.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.94.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.94.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.94.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.94.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.94.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.94.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.94.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.95.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.95.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.95.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.95.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.95.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.95.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.95.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.95.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.95.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.96.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.96.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.96.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.96.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.96.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.96.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.96.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.96.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.96.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.97.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.97.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.97.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.97.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.97.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.97.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.97.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.97.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.97.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.98.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.98.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.98.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.98.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.98.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.98.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.98.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.98.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.98.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.99.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.99.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.99.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.99.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.99.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.99.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.experts.99.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.gate.weight": "model-00002-of-00004.safetensors", - "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.0.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.0.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.0.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.0.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.0.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.0.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.0.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.0.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.0.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.1.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.1.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.1.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.1.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.1.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.1.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.1.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.1.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.1.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.10.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.10.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.10.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.10.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.10.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.10.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.10.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.10.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.10.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.100.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.100.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.100.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.100.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.100.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.100.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.100.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.100.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.100.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.101.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.101.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.101.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.101.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.101.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.101.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.101.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.101.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.101.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.102.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.102.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.102.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.102.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.102.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.102.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.102.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.102.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.102.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.103.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.103.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.103.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.103.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.103.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.103.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.103.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.103.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.103.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.104.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.104.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.104.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.104.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.104.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.104.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.104.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.104.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.104.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.105.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.105.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.105.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.105.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.105.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.105.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.105.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.105.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.105.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.106.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.106.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.106.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.106.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.106.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.106.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.106.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.106.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.106.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.107.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.107.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.107.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.107.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.107.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.107.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.107.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.107.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.107.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.108.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.108.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.108.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.108.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.108.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.108.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.108.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.108.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.108.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.109.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.109.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.109.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.109.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.109.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.109.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.109.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.109.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.109.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.11.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.11.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.11.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.11.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.11.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.11.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.11.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.11.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.11.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.110.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.110.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.110.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.110.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.110.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.110.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.110.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.110.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.110.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.111.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.111.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.111.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.111.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.111.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.111.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.111.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.111.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.111.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.112.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.112.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.112.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.112.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.112.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.112.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.112.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.112.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.112.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.113.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.113.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.113.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.113.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.113.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.113.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.113.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.113.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.113.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.114.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.114.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.114.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.114.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.114.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.114.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.114.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.114.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.114.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.115.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.115.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.115.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.115.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.115.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.115.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.115.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.115.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.115.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.116.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.116.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.116.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.116.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.116.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.116.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.116.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.116.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.116.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.117.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.117.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.117.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.117.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.117.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.117.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.117.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.117.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.117.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.118.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.118.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.118.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.118.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.118.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.118.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.118.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.118.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.118.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.119.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.119.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.119.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.119.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.119.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.119.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.119.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.119.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.119.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.12.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.12.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.12.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.12.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.12.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.12.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.12.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.12.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.12.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.120.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.120.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.120.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.120.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.120.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.120.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.120.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.120.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.120.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.121.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.121.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.121.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.121.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.121.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.121.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.121.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.121.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.121.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.122.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.122.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.122.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.122.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.122.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.122.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.122.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.122.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.122.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.123.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.123.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.123.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.123.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.123.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.123.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.123.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.123.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.123.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.124.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.124.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.124.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.124.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.124.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.124.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.124.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.124.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.124.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.125.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.125.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.125.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.125.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.125.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.125.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.125.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.125.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.125.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.126.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.126.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.126.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.126.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.126.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.126.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.126.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.126.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.126.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.127.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.127.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.127.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.127.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.127.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.127.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.127.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.127.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.127.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.13.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.13.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.13.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.13.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.13.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.13.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.13.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.13.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.13.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.14.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.14.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.14.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.14.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.14.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.14.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.14.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.14.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.14.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.15.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.15.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.15.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.15.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.15.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.15.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.15.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.15.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.15.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.16.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.16.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.16.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.16.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.16.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.16.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.16.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.16.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.16.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.17.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.17.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.17.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.17.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.17.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.17.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.17.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.17.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.17.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.18.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.18.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.18.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.18.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.18.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.18.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.18.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.18.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.18.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.19.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.19.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.19.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.19.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.19.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.19.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.19.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.19.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.19.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.2.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.2.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.2.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.2.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.2.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.2.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.2.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.2.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.2.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.20.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.20.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.20.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.20.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.20.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.20.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.20.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.20.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.20.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.21.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.21.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.21.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.21.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.21.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.21.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.21.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.21.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.21.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.22.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.22.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.22.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.22.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.22.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.22.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.22.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.22.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.22.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.23.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.23.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.23.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.23.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.23.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.23.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.23.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.23.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.23.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.24.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.24.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.24.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.24.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.24.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.24.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.24.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.24.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.24.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.25.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.25.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.25.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.25.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.25.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.25.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.25.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.25.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.25.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.26.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.26.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.26.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.26.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.26.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.26.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.26.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.26.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.26.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.27.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.27.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.27.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.27.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.27.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.27.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.27.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.27.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.27.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.28.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.28.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.28.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.28.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.28.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.28.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.28.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.28.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.28.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.29.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.29.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.29.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.29.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.29.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.29.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.29.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.29.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.29.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.3.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.3.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.3.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.3.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.3.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.3.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.3.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.3.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.3.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.30.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.30.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.30.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.30.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.30.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.30.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.30.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.30.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.30.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.31.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.31.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.31.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.31.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.31.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.31.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.31.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.31.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.31.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.32.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.32.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.32.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.32.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.32.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.32.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.32.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.32.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.32.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.33.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.33.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.33.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.33.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.33.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.33.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.33.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.33.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.33.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.34.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.34.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.34.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.34.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.34.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.34.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.34.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.34.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.34.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.35.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.35.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.35.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.35.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.35.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.35.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.35.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.35.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.35.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.36.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.36.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.36.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.36.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.36.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.36.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.36.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.36.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.36.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.37.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.37.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.37.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.37.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.37.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.37.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.37.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.37.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.37.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.38.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.38.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.38.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.38.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.38.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.38.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.38.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.38.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.38.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.39.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.39.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.39.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.39.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.39.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.39.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.39.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.39.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.39.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.4.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.4.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.4.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.4.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.4.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.4.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.4.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.4.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.4.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.40.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.40.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.40.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.40.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.40.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.40.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.40.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.40.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.40.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.41.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.41.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.41.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.41.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.41.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.41.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.41.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.41.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.41.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.42.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.42.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.42.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.42.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.42.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.42.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.42.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.42.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.42.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.43.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.43.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.43.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.43.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.43.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.43.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.43.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.43.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.43.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.44.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.44.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.44.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.44.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.44.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.44.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.44.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.44.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.44.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.45.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.45.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.45.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.45.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.45.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.45.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.45.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.45.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.45.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.46.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.46.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.46.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.46.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.46.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.46.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.46.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.46.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.46.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.47.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.47.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.47.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.47.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.47.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.47.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.47.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.47.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.47.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.48.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.48.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.48.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.48.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.48.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.48.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.48.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.48.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.48.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.49.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.49.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.49.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.49.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.49.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.49.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.49.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.49.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.49.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.5.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.5.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.5.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.5.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.5.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.5.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.5.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.5.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.5.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.50.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.50.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.50.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.50.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.50.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.50.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.50.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.50.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.50.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.51.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.51.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.51.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.51.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.51.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.51.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.51.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.51.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.51.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.52.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.52.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.52.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.52.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.52.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.52.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.52.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.52.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.52.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.53.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.53.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.53.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.53.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.53.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.53.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.53.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.53.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.53.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.54.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.54.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.54.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.54.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.54.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.54.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.54.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.54.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.54.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.55.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.55.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.55.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.55.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.55.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.55.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.55.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.55.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.55.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.56.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.56.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.56.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.56.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.56.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.56.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.56.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.56.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.56.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.57.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.57.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.57.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.57.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.57.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.57.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.57.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.57.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.57.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.58.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.58.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.58.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.58.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.58.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.58.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.58.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.58.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.58.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.59.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.59.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.59.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.59.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.59.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.59.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.59.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.59.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.59.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.6.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.6.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.6.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.6.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.6.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.6.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.6.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.6.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.6.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.60.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.60.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.60.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.60.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.60.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.60.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.60.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.60.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.60.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.61.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.61.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.61.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.61.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.61.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.61.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.61.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.61.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.61.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.62.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.62.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.62.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.62.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.62.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.62.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.62.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.62.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.62.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.63.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.63.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.63.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.63.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.63.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.63.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.63.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.63.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.63.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.64.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.64.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.64.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.64.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.64.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.64.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.64.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.64.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.64.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.65.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.65.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.65.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.65.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.65.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.65.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.65.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.65.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.65.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.66.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.66.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.66.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.66.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.66.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.66.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.66.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.66.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.66.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.67.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.67.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.67.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.67.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.67.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.67.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.67.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.67.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.67.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.68.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.68.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.68.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.68.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.68.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.68.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.68.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.68.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.68.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.69.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.69.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.69.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.69.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.69.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.69.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.69.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.69.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.69.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.7.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.7.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.7.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.7.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.7.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.7.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.7.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.7.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.7.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.70.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.70.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.70.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.70.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.70.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.70.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.70.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.70.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.70.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.71.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.71.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.71.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.71.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.71.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.71.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.71.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.71.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.71.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.72.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.72.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.72.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.72.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.72.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.72.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.72.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.72.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.72.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.73.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.73.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.73.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.73.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.73.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.73.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.73.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.73.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.73.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.74.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.74.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.74.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.74.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.74.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.74.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.74.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.74.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.74.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.75.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.75.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.75.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.75.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.75.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.75.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.75.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.75.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.75.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.76.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.76.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.76.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.76.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.76.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.76.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.76.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.76.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.76.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.77.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.77.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.77.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.77.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.77.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.77.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.77.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.77.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.77.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.78.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.78.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.78.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.78.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.78.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.78.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.78.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.78.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.78.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.79.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.79.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.79.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.79.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.79.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.79.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.79.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.79.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.79.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.8.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.8.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.8.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.8.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.8.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.8.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.8.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.8.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.8.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.80.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.80.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.80.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.80.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.80.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.80.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.80.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.80.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.80.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.81.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.81.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.81.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.81.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.81.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.81.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.81.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.81.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.81.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.82.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.82.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.82.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.82.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.82.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.82.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.82.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.82.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.82.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.83.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.83.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.83.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.83.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.83.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.83.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.83.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.83.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.83.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.84.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.84.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.84.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.84.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.84.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.84.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.84.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.84.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.84.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.85.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.85.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.85.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.85.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.85.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.85.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.85.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.85.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.85.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.86.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.86.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.86.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.86.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.86.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.86.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.86.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.86.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.86.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.87.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.87.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.87.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.87.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.87.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.87.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.87.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.87.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.87.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.88.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.88.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.88.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.88.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.88.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.88.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.88.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.88.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.88.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.89.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.89.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.89.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.89.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.89.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.89.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.89.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.89.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.89.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.9.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.9.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.9.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.9.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.9.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.9.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.9.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.9.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.9.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.90.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.90.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.90.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.90.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.90.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.90.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.90.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.90.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.90.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.91.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.91.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.91.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.91.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.91.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.91.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.91.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.91.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.91.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.92.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.92.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.92.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.92.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.92.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.92.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.92.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.92.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.92.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.93.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.93.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.93.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.93.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.93.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.93.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.93.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.93.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.93.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.94.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.94.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.94.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.94.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.94.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.94.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.94.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.94.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.94.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.95.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.95.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.95.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.95.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.95.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.95.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.95.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.95.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.95.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.96.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.96.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.96.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.96.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.96.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.96.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.96.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.96.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.96.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.97.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.97.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.97.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.97.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.97.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.97.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.97.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.97.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.97.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.98.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.98.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.98.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.98.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.98.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.98.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.98.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.98.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.98.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.99.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.99.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.99.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.99.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.99.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.99.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.experts.99.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.mlp.gate.weight": "model-00002-of-00004.safetensors", - "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.28.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.0.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.0.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.0.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.0.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.0.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.0.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.0.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.0.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.0.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.1.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.1.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.1.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.1.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.1.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.1.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.1.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.1.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.1.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.10.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.10.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.10.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.10.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.10.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.10.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.10.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.10.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.10.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.100.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.100.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.100.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -25842,15 +25842,15 @@ "model.layers.29.mlp.experts.109.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.109.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.109.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.11.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.11.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.11.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.11.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.11.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.11.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.11.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.11.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.11.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.110.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.110.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.110.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -25941,15 +25941,15 @@ "model.layers.29.mlp.experts.119.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.119.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.119.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.12.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.12.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.12.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.12.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.12.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.12.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.12.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.12.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.12.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.120.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.120.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.120.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -26022,33 +26022,33 @@ "model.layers.29.mlp.experts.127.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.127.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.127.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.13.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.13.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.13.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.13.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.13.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.13.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.13.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.13.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.13.up_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.14.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.14.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.14.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.14.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.14.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.14.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.14.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.14.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.14.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.15.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.15.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.15.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.15.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.15.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.15.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.15.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.15.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.15.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.16.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.16.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.16.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -26085,15 +26085,15 @@ "model.layers.29.mlp.experts.19.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.19.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.19.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.2.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.2.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.2.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.2.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.2.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.2.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.2.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.2.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.2.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.20.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.20.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.20.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -26184,15 +26184,15 @@ "model.layers.29.mlp.experts.29.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.29.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.29.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.3.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.3.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.3.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.3.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.3.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.3.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.3.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.3.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.3.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.30.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.30.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.30.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -26283,15 +26283,15 @@ "model.layers.29.mlp.experts.39.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.39.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.39.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.4.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.4.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.4.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.4.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.4.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.4.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.4.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.4.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.4.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.40.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.40.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.40.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -26382,15 +26382,15 @@ "model.layers.29.mlp.experts.49.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.49.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.49.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.5.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.5.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.5.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.5.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.5.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.5.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.5.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.5.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.5.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.50.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.50.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.50.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -26481,15 +26481,15 @@ "model.layers.29.mlp.experts.59.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.59.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.59.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.6.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.6.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.6.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.6.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.6.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.6.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.6.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.6.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.6.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.60.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.60.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.60.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -26580,15 +26580,15 @@ "model.layers.29.mlp.experts.69.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.69.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.69.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.7.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.7.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.7.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.7.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.7.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.7.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.7.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.7.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.7.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.70.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.70.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.70.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -26679,15 +26679,15 @@ "model.layers.29.mlp.experts.79.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.79.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.79.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.8.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.8.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.8.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.8.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.8.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.8.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.8.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.8.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.8.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.80.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.80.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.80.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -26778,15 +26778,15 @@ "model.layers.29.mlp.experts.89.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.89.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.89.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.experts.9.down_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.9.down_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.9.down_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.9.gate_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.9.gate_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.9.gate_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.9.up_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.9.up_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.mlp.experts.9.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.90.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.90.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.90.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -26877,22 +26877,22 @@ "model.layers.29.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.29.mlp.experts.99.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.gate.weight": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", - "model.layers.29.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", - "model.layers.29.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", - "model.layers.29.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", - "model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", - "model.layers.29.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.experts.0.down_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.3.mlp.experts.0.down_proj.weight_scale": "model-00001-of-00004.safetensors", @@ -40921,7 +40921,7 @@ "model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", - "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.40.mlp.experts.0.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.40.mlp.experts.0.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.40.mlp.experts.0.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -41183,42 +41183,42 @@ "model.layers.40.mlp.experts.123.up_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.40.mlp.experts.123.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.40.mlp.experts.123.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.124.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.124.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.124.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.124.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.124.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.experts.124.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.124.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.124.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.124.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.124.gate_proj.weight_scale": "model-00004-of-00004.safetensors", "model.layers.40.mlp.experts.124.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.124.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.124.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.124.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.125.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.125.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.125.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.125.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.125.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.125.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.125.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.125.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.125.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.126.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.126.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.126.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.126.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.126.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.126.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.126.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.126.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.126.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.127.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.127.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.127.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.127.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.127.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.127.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.127.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.127.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.experts.127.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.experts.124.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.124.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.124.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.125.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.125.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.125.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.125.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.125.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.125.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.125.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.125.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.125.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.126.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.126.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.126.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.126.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.126.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.126.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.126.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.126.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.126.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.127.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.127.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.127.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.127.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.127.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.127.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.127.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.127.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.40.mlp.experts.127.up_proj.weight_shape": "model-00004-of-00004.safetensors", "model.layers.40.mlp.experts.13.down_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.40.mlp.experts.13.down_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.40.mlp.experts.13.down_proj.weight_shape": "model-00003-of-00004.safetensors", @@ -42075,7 +42075,7 @@ "model.layers.40.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.40.mlp.experts.99.up_proj.weight_shape": "model-00003-of-00004.safetensors", "model.layers.40.mlp.gate.weight": "model-00003-of-00004.safetensors", - "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.40.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.40.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.40.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", @@ -42090,3541 +42090,3541 @@ "model.layers.40.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", "model.layers.40.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.layers.40.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.0.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.0.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.0.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.0.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.0.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.0.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.0.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.0.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.0.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.1.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.1.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.1.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.1.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.1.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.1.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.1.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.1.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.1.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.10.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.10.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.10.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.10.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.10.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.10.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.10.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.10.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.10.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.100.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.100.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.100.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.100.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.100.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.100.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.100.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.100.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.100.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.101.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.101.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.101.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.101.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.101.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.101.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.101.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.101.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.101.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.102.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.102.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.102.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.102.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.102.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.102.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.102.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.102.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.102.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.103.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.103.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.103.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.103.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.103.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.103.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.103.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.103.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.103.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.104.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.104.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.104.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.104.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.104.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.104.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.104.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.104.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.104.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.105.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.105.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.105.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.105.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.105.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.105.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.105.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.105.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.105.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.106.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.106.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.106.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.106.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.106.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.106.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.106.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.106.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.106.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.107.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.107.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.107.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.107.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.107.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.107.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.107.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.107.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.107.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.108.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.108.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.108.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.108.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.108.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.108.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.108.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.108.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.108.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.109.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.109.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.109.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.109.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.109.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.109.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.109.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.109.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.109.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.11.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.11.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.11.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.11.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.11.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.11.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.11.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.11.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.11.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.110.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.110.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.110.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.110.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.110.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.110.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.110.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.110.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.110.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.111.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.111.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.111.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.111.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.111.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.111.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.111.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.111.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.111.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.112.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.112.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.112.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.112.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.112.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.112.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.112.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.112.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.112.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.113.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.113.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.113.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.113.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.113.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.113.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.113.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.113.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.113.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.114.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.114.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.114.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.114.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.114.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.114.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.114.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.114.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.114.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.115.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.115.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.115.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.115.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.115.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.115.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.115.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.115.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.115.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.116.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.116.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.116.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.116.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.116.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.116.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.116.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.116.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.116.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.117.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.117.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.117.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.117.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.117.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.117.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.117.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.117.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.117.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.118.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.118.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.118.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.118.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.118.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.118.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.118.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.118.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.118.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.119.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.119.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.119.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.119.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.119.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.119.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.119.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.119.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.119.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.12.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.12.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.12.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.12.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.12.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.12.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.12.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.12.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.12.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.120.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.120.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.120.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.120.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.120.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.120.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.120.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.120.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.120.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.121.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.121.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.121.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.121.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.121.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.121.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.121.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.121.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.121.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.122.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.122.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.122.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.122.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.122.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.122.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.122.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.122.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.122.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.123.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.123.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.123.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.123.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.123.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.123.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.123.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.123.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.123.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.124.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.124.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.124.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.124.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.124.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.124.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.124.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.124.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.124.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.125.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.125.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.125.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.125.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.125.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.125.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.125.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.125.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.125.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.126.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.126.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.126.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.126.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.126.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.126.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.126.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.126.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.126.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.127.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.127.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.127.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.127.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.127.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.127.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.127.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.127.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.127.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.13.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.13.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.13.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.13.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.13.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.13.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.13.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.13.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.13.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.14.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.14.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.14.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.14.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.14.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.14.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.14.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.14.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.14.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.15.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.15.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.15.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.15.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.15.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.15.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.15.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.15.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.15.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.16.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.16.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.16.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.16.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.16.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.16.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.16.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.16.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.16.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.17.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.17.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.17.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.17.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.17.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.17.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.17.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.17.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.17.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.18.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.18.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.18.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.18.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.18.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.18.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.18.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.18.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.18.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.19.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.19.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.19.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.19.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.19.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.19.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.19.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.19.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.19.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.2.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.2.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.2.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.2.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.2.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.2.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.2.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.2.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.2.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.20.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.20.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.20.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.20.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.20.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.20.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.20.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.20.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.20.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.21.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.21.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.21.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.21.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.21.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.21.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.21.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.21.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.21.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.22.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.22.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.22.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.22.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.22.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.22.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.22.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.22.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.22.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.23.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.23.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.23.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.23.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.23.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.23.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.23.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.23.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.23.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.24.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.24.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.24.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.24.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.24.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.24.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.24.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.24.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.24.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.25.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.25.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.25.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.25.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.25.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.25.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.25.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.25.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.25.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.26.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.26.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.26.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.26.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.26.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.26.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.26.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.26.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.26.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.27.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.27.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.27.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.27.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.27.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.27.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.27.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.27.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.27.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.28.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.28.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.28.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.28.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.28.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.28.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.28.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.28.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.28.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.29.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.29.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.29.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.29.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.29.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.29.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.29.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.29.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.29.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.3.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.3.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.3.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.3.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.3.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.3.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.3.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.3.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.3.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.30.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.30.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.30.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.30.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.30.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.30.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.30.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.30.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.30.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.31.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.31.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.31.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.31.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.31.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.31.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.31.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.31.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.31.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.32.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.32.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.32.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.32.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.32.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.32.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.32.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.32.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.32.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.33.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.33.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.33.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.33.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.33.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.33.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.33.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.33.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.33.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.34.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.34.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.34.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.34.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.34.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.34.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.34.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.34.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.34.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.35.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.35.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.35.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.35.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.35.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.35.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.35.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.35.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.35.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.36.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.36.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.36.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.36.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.36.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.36.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.36.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.36.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.36.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.37.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.37.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.37.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.37.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.37.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.37.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.37.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.37.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.37.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.38.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.38.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.38.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.38.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.38.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.38.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.38.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.38.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.38.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.39.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.39.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.39.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.39.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.39.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.39.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.39.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.39.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.39.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.4.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.4.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.4.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.4.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.4.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.4.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.4.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.4.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.4.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.40.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.40.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.40.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.40.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.40.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.40.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.40.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.40.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.40.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.41.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.41.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.41.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.41.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.41.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.41.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.41.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.41.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.41.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.42.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.42.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.42.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.42.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.42.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.42.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.42.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.42.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.42.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.43.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.43.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.43.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.43.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.43.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.43.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.43.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.43.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.43.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.44.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.44.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.44.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.44.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.44.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.44.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.44.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.44.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.44.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.45.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.45.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.45.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.45.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.45.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.45.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.45.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.45.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.45.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.46.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.46.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.46.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.46.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.46.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.46.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.46.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.46.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.46.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.47.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.47.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.47.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.47.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.47.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.47.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.47.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.47.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.47.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.48.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.48.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.48.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.48.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.48.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.48.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.48.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.48.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.48.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.49.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.49.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.49.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.49.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.49.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.49.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.49.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.49.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.49.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.5.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.5.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.5.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.5.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.5.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.5.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.5.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.5.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.5.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.50.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.50.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.50.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.50.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.50.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.50.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.50.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.50.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.50.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.51.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.51.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.51.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.51.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.51.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.51.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.51.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.51.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.51.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.52.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.52.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.52.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.52.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.52.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.52.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.52.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.52.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.52.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.53.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.53.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.53.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.53.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.53.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.53.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.53.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.53.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.53.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.54.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.54.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.54.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.54.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.54.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.54.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.54.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.54.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.54.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.55.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.55.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.55.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.55.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.55.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.55.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.55.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.55.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.55.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.56.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.56.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.56.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.56.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.56.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.56.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.56.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.56.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.56.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.57.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.57.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.57.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.57.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.57.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.57.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.57.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.57.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.57.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.58.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.58.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.58.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.58.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.58.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.58.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.58.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.58.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.58.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.59.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.59.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.59.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.59.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.59.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.59.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.59.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.59.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.59.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.6.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.6.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.6.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.6.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.6.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.6.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.6.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.6.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.6.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.60.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.60.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.60.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.60.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.60.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.60.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.60.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.60.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.60.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.61.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.61.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.61.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.61.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.61.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.61.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.61.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.61.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.61.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.62.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.62.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.62.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.62.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.62.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.62.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.62.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.62.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.62.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.63.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.63.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.63.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.63.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.63.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.63.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.63.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.63.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.63.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.64.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.64.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.64.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.64.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.64.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.64.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.64.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.64.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.64.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.65.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.65.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.65.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.65.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.65.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.65.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.65.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.65.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.65.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.66.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.66.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.66.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.66.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.66.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.66.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.66.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.66.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.66.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.67.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.67.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.67.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.67.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.67.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.67.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.67.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.67.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.67.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.68.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.68.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.68.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.68.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.68.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.68.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.68.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.68.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.68.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.69.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.69.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.69.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.69.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.69.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.69.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.69.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.69.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.69.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.7.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.7.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.7.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.7.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.7.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.7.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.7.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.7.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.7.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.70.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.70.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.70.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.70.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.70.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.70.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.70.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.70.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.70.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.71.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.71.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.71.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.71.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.71.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.71.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.71.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.71.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.71.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.72.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.72.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.72.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.72.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.72.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.72.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.72.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.72.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.72.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.73.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.73.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.73.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.73.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.73.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.73.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.73.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.73.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.73.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.74.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.74.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.74.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.74.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.74.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.74.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.74.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.74.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.74.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.75.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.75.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.75.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.75.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.75.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.75.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.75.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.75.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.75.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.76.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.76.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.76.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.76.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.76.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.76.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.76.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.76.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.76.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.77.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.77.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.77.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.77.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.77.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.77.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.77.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.77.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.77.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.78.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.78.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.78.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.78.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.78.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.78.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.78.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.78.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.78.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.79.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.79.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.79.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.79.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.79.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.79.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.79.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.79.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.79.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.8.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.8.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.8.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.8.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.8.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.8.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.8.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.8.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.8.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.80.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.80.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.80.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.80.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.80.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.80.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.80.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.80.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.80.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.81.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.81.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.81.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.81.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.81.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.81.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.81.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.81.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.81.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.82.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.82.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.82.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.82.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.82.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.82.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.82.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.82.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.82.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.83.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.83.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.83.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.83.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.83.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.83.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.83.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.83.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.83.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.84.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.84.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.84.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.84.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.84.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.84.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.84.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.84.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.84.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.85.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.85.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.85.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.85.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.85.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.85.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.85.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.85.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.85.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.86.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.86.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.86.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.86.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.86.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.86.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.86.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.86.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.86.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.87.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.87.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.87.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.87.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.87.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.87.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.87.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.87.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.87.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.88.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.88.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.88.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.88.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.88.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.88.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.88.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.88.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.88.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.89.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.89.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.89.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.89.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.89.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.89.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.89.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.89.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.89.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.9.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.9.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.9.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.9.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.9.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.9.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.9.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.9.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.9.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.90.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.90.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.90.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.90.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.90.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.90.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.90.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.90.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.90.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.91.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.91.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.91.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.91.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.91.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.91.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.91.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.91.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.91.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.92.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.92.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.92.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.92.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.92.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.92.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.92.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.92.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.92.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.93.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.93.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.93.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.93.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.93.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.93.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.93.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.93.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.93.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.94.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.94.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.94.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.94.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.94.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.94.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.94.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.94.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.94.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.95.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.95.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.95.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.95.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.95.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.95.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.95.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.95.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.95.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.96.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.96.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.96.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.96.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.96.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.96.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.96.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.96.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.96.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.97.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.97.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.97.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.97.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.97.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.97.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.97.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.97.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.97.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.98.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.98.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.98.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.98.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.98.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.98.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.98.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.98.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.98.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.99.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.99.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.99.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.99.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.99.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.99.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.experts.99.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.gate.weight": "model-00003-of-00004.safetensors", - "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.0.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.0.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.0.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.0.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.0.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.0.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.0.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.0.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.0.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.1.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.1.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.1.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.1.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.1.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.1.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.1.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.1.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.1.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.10.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.10.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.10.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.10.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.10.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.10.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.10.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.10.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.10.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.100.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.100.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.100.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.100.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.100.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.100.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.100.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.100.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.100.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.101.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.101.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.101.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.101.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.101.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.101.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.101.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.101.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.101.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.102.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.102.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.102.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.102.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.102.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.102.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.102.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.102.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.102.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.103.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.103.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.103.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.103.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.103.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.103.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.103.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.103.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.103.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.104.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.104.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.104.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.104.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.104.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.104.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.104.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.104.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.104.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.105.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.105.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.105.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.105.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.105.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.105.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.105.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.105.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.105.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.106.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.106.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.106.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.106.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.106.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.106.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.106.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.106.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.106.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.107.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.107.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.107.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.107.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.107.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.107.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.107.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.107.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.107.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.108.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.108.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.108.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.108.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.108.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.108.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.108.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.108.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.108.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.109.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.109.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.109.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.109.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.109.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.109.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.109.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.109.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.109.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.11.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.11.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.11.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.11.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.11.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.11.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.11.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.11.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.11.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.110.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.110.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.110.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.110.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.110.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.110.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.110.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.110.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.110.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.111.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.111.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.111.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.111.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.111.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.111.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.111.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.111.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.111.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.112.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.112.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.112.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.112.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.112.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.112.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.112.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.112.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.112.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.113.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.113.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.113.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.113.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.113.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.113.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.113.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.113.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.113.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.114.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.114.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.114.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.114.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.114.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.114.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.114.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.114.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.114.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.115.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.115.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.115.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.115.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.115.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.115.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.115.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.115.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.115.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.116.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.116.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.116.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.116.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.116.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.116.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.116.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.116.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.116.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.117.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.117.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.117.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.117.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.117.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.117.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.117.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.117.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.117.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.118.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.118.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.118.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.118.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.118.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.118.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.118.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.118.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.118.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.119.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.119.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.119.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.119.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.119.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.119.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.119.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.119.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.119.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.12.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.12.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.12.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.12.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.12.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.12.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.12.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.12.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.12.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.120.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.120.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.120.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.120.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.120.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.120.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.120.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.120.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.120.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.121.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.121.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.121.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.121.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.121.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.121.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.121.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.121.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.121.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.122.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.122.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.122.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.122.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.122.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.122.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.122.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.122.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.122.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.123.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.123.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.123.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.123.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.123.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.123.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.123.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.123.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.123.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.124.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.124.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.124.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.124.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.124.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.124.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.124.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.124.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.124.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.125.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.125.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.125.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.125.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.125.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.125.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.125.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.125.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.125.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.126.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.126.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.126.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.126.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.126.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.126.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.126.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.126.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.126.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.127.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.127.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.127.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.127.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.127.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.127.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.127.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.127.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.127.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.13.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.13.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.13.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.13.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.13.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.13.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.13.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.13.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.13.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.14.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.14.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.14.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.14.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.14.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.14.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.14.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.14.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.14.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.15.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.15.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.15.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.15.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.15.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.15.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.15.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.15.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.15.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.16.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.16.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.16.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.16.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.16.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.16.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.16.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.16.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.16.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.17.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.17.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.17.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.17.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.17.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.17.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.17.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.17.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.17.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.18.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.18.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.18.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.18.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.18.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.18.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.18.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.18.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.18.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.19.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.19.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.19.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.19.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.19.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.19.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.19.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.19.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.19.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.2.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.2.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.2.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.2.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.2.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.2.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.2.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.2.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.2.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.20.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.20.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.20.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.20.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.20.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.20.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.20.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.20.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.20.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.21.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.21.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.21.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.21.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.21.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.21.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.21.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.21.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.21.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.22.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.22.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.22.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.22.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.22.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.22.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.22.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.22.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.22.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.23.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.23.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.23.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.23.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.23.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.23.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.23.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.23.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.23.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.24.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.24.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.24.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.24.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.24.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.24.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.24.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.24.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.24.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.25.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.25.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.25.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.25.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.25.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.25.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.25.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.25.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.25.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.26.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.26.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.26.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.26.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.26.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.26.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.26.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.26.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.26.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.27.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.27.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.27.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.27.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.27.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.27.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.27.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.27.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.27.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.28.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.28.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.28.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.28.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.28.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.28.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.28.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.28.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.28.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.29.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.29.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.29.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.29.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.29.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.29.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.29.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.29.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.29.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.3.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.3.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.3.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.3.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.3.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.3.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.3.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.3.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.3.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.30.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.30.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.30.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.30.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.30.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.30.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.30.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.30.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.30.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.31.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.31.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.31.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.31.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.31.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.31.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.31.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.31.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.31.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.32.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.32.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.32.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.32.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.32.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.32.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.32.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.32.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.32.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.33.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.33.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.33.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.33.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.33.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.33.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.33.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.33.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.33.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.34.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.34.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.34.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.34.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.34.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.34.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.34.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.34.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.34.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.35.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.35.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.35.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.35.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.35.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.35.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.35.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.35.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.35.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.36.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.36.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.36.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.36.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.36.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.36.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.36.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.36.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.36.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.37.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.37.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.37.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.37.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.37.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.37.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.37.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.37.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.37.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.38.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.38.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.38.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.38.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.38.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.38.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.38.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.38.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.38.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.39.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.39.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.39.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.39.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.39.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.39.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.39.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.39.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.39.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.4.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.4.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.4.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.4.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.4.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.4.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.4.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.4.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.4.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.40.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.40.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.40.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.40.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.40.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.40.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.40.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.40.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.40.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.41.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.41.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.41.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.41.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.41.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.41.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.41.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.41.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.41.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.42.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.42.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.42.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.42.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.42.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.42.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.42.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.42.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.42.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.43.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.43.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.43.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.43.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.43.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.43.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.43.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.43.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.43.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.44.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.44.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.44.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.44.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.44.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.44.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.44.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.44.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.44.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.45.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.45.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.45.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.45.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.45.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.45.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.45.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.45.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.45.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.46.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.46.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.46.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.46.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.46.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.46.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.46.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.46.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.46.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.47.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.47.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.47.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.47.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.47.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.47.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.47.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.47.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.47.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.48.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.48.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.48.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.48.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.48.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.48.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.48.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.48.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.48.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.49.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.49.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.49.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.49.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.49.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.49.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.49.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.49.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.49.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.5.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.5.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.5.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.5.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.5.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.5.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.5.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.5.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.5.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.50.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.50.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.50.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.50.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.50.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.50.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.50.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.50.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.50.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.51.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.51.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.51.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.51.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.51.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.51.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.51.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.51.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.51.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.52.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.52.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.52.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.52.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.52.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.52.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.52.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.52.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.52.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.53.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.53.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.53.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.53.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.53.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.53.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.53.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.53.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.53.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.54.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.54.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.54.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.54.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.54.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.54.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.54.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.54.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.54.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.55.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.55.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.55.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.55.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.55.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.55.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.55.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.55.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.55.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.56.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.56.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.56.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.56.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.56.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.56.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.56.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.56.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.56.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.57.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.57.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.57.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.57.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.57.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.57.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.57.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.57.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.57.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.58.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.58.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.58.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.58.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.58.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.58.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.58.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.58.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.58.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.59.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.59.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.59.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.59.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.59.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.59.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.59.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.59.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.59.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.6.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.6.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.6.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.6.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.6.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.6.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.6.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.6.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.6.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.60.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.60.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.60.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.60.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.60.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.60.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.60.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.60.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.60.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.61.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.61.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.61.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.61.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.61.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.61.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.61.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.61.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.61.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.62.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.62.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.62.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.62.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.62.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.62.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.62.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.62.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.62.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.63.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.63.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.63.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.63.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.63.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.63.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.63.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.63.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.63.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.64.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.64.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.64.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.64.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.64.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.64.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.64.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.64.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.64.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.65.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.65.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.65.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.65.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.65.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.65.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.65.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.65.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.65.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.66.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.66.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.66.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.66.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.66.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.66.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.66.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.66.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.66.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.67.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.67.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.67.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.67.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.67.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.67.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.67.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.67.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.67.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.68.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.68.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.68.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.68.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.68.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.68.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.68.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.68.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.68.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.69.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.69.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.69.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.69.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.69.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.69.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.69.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.69.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.69.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.7.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.7.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.7.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.7.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.7.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.7.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.7.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.7.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.7.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.70.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.70.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.70.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.70.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.70.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.70.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.70.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.70.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.70.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.71.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.71.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.71.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.71.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.71.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.71.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.71.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.71.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.71.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.72.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.72.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.72.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.72.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.72.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.72.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.72.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.72.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.72.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.73.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.73.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.73.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.73.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.73.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.73.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.73.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.73.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.73.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.74.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.74.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.74.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.74.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.74.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.74.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.74.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.74.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.74.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.75.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.75.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.75.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.75.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.75.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.75.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.75.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.75.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.75.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.76.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.76.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.76.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.76.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.76.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.76.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.76.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.76.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.76.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.77.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.77.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.77.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.77.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.77.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.77.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.77.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.77.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.77.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.78.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.78.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.78.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.78.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.78.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.78.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.78.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.78.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.78.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.79.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.79.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.79.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.79.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.79.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.79.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.79.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.79.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.79.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.8.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.8.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.8.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.8.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.8.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.8.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.8.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.8.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.8.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.80.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.80.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.80.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.80.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.80.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.80.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.80.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.80.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.80.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.81.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.81.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.81.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.81.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.81.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.81.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.81.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.81.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.81.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.82.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.82.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.82.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.82.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.82.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.82.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.82.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.82.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.82.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.83.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.83.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.83.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.83.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.83.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.83.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.83.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.83.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.83.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.84.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.84.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.84.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.84.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.84.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.84.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.84.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.84.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.84.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.85.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.85.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.85.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.85.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.85.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.85.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.85.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.85.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.85.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.86.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.86.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.86.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.86.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.86.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.86.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.86.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.86.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.86.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.87.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.87.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.87.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.87.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.87.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.87.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.87.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.87.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.87.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.88.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.88.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.88.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.88.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.88.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.88.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.88.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.88.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.88.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.89.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.89.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.89.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.89.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.89.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.89.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.89.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.89.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.89.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.9.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.9.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.9.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.9.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.9.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.9.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.9.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.9.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.9.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.90.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.90.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.90.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.90.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.90.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.90.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.90.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.90.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.90.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.91.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.91.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.91.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.91.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.91.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.91.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.91.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.91.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.91.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.92.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.92.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.92.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.92.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.92.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.92.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.92.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.92.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.92.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.93.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.93.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.93.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.93.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.93.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.93.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.93.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.93.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.93.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.94.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.94.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.94.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.94.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.94.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.94.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.94.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.94.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.94.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.95.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.95.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.95.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.95.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.95.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.95.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.95.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.95.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.95.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.96.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.96.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.96.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.96.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.96.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.96.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.96.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.96.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.96.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.97.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.97.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.97.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.97.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.97.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.97.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.97.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.97.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.97.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.98.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.98.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.98.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.98.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.98.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.98.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.98.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.98.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.98.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.99.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.99.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.99.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.99.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.99.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.99.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.experts.99.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.gate.weight": "model-00003-of-00004.safetensors", - "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.0.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.0.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.0.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.0.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.0.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.0.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.0.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.0.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.0.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.1.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.1.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.1.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.1.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.1.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.1.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.1.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.1.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.1.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.10.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.10.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.10.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.10.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.10.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.10.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.10.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.10.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.10.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.100.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.100.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.100.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.100.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.100.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.100.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.100.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.100.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.100.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.101.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.101.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.101.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.101.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.101.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.101.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.101.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.101.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.101.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.102.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.102.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.102.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.102.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.102.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.102.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.102.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.102.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.102.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.103.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.103.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.103.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.103.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.103.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.103.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.103.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.103.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.103.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.104.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.104.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.104.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.104.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.104.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.104.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.104.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.104.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.104.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.105.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.105.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.105.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.105.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.105.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.105.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.105.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.105.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.105.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.106.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.106.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.106.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.106.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.106.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.106.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.106.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.106.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.106.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.107.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.107.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.107.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.107.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.107.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.107.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.107.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.107.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.107.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.108.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.108.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.108.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.108.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.108.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.108.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.108.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.108.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.108.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.109.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.109.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.109.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.109.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.109.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.109.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.109.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.109.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.109.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.11.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.11.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.11.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.11.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.11.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.11.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.11.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.11.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.11.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.110.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.110.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.110.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.110.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.110.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.110.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.110.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.110.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.110.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.111.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.111.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.111.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.111.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.111.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.111.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.111.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.111.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.111.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.112.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.112.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.112.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.112.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.112.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.112.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.112.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.112.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.112.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.113.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.113.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.113.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.113.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.113.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.113.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.113.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.113.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.113.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.114.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.114.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.114.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.114.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.114.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.114.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.114.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.114.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.114.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.115.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.115.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.115.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.115.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.115.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.115.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.115.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.115.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.115.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.116.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.116.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.116.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.116.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.116.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.116.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.116.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.116.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.116.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.117.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.117.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.117.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.117.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.117.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.117.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.117.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.117.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.117.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.118.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.118.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.118.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.118.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.118.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.118.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.118.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.118.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.118.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.119.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.119.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.119.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.119.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.119.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.119.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.119.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.119.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.119.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.12.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.12.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.12.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.12.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.12.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.12.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.12.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.12.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.12.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.120.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.120.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.120.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.120.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.120.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.120.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.120.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.120.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.120.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.121.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.121.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.121.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.121.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.121.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.121.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.121.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.121.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.121.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.122.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.122.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.122.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.122.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.122.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.122.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.122.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.122.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.122.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.123.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.123.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.123.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.123.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.123.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.123.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.123.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.123.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.123.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.124.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.124.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.124.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.124.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.124.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.124.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.124.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.124.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.124.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.125.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.125.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.125.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.125.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.125.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.125.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.125.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.125.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.125.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.126.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.126.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.126.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.126.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.126.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.126.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.126.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.126.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.126.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.127.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.127.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.127.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.127.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.127.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.127.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.127.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.127.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.127.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.13.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.13.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.13.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.13.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.13.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.13.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.13.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.13.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.13.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.14.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.14.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.14.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.14.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.14.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.14.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.14.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.14.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.14.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.15.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.15.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.15.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.15.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.15.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.15.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.15.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.15.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.15.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.16.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.16.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.16.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.16.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.16.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.16.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.16.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.16.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.16.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.17.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.17.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.17.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.17.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.17.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.17.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.17.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.17.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.17.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.18.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.18.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.18.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.18.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.18.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.18.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.18.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.18.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.18.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.19.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.19.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.19.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.19.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.19.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.19.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.19.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.19.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.19.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.2.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.2.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.2.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.2.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.2.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.2.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.2.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.2.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.2.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.20.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.20.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.20.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.20.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.20.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.20.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.20.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.20.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.20.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.21.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.21.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.21.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.21.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.21.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.21.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.21.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.21.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.21.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.22.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.22.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.22.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.22.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.22.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.22.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.22.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.22.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.22.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.23.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.23.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.23.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.23.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.23.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.23.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.23.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.23.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.23.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.24.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.24.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.24.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.24.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.24.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.24.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.24.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.24.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.24.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.25.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.25.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.25.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.25.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.25.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.25.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.25.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.25.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.25.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.26.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.26.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.26.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.26.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.26.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.26.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.26.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.26.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.26.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.27.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.27.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.27.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.27.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.27.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.27.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.27.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.27.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.27.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.28.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.28.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.28.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.28.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.28.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.28.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.28.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.28.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.28.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.29.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.29.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.29.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.29.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.29.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.29.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.29.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.29.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.29.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.3.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.3.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.3.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.3.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.3.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.3.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.3.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.3.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.3.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.30.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.30.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.30.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.30.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.30.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.30.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.30.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.30.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.30.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.31.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.31.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.31.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.31.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.31.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.31.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.31.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.31.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.31.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.32.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.32.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.32.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.32.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.32.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.32.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.32.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.32.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.32.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.33.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.33.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.33.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.33.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.33.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.33.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.33.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.33.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.33.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.34.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.34.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.34.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.34.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.34.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.34.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.34.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.34.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.34.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.35.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.35.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.35.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.35.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.35.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.35.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.35.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.35.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.35.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.36.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.36.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.36.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.36.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.36.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.36.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.36.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.36.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.36.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.37.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.37.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.37.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.37.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.37.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.37.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.37.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.37.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.37.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.38.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.38.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.38.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.38.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.38.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.38.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.38.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.38.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.38.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.39.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.39.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.39.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.39.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.39.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.39.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.39.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.39.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.39.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.4.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.4.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.4.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.4.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.4.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.4.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.4.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.4.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.4.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.40.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.40.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.40.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.40.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.40.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.40.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.40.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.40.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.40.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.41.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.41.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.41.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.41.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.41.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.41.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.41.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.41.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.41.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.42.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.42.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.42.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.42.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.42.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.42.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.42.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.42.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.42.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.43.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.43.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.43.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.43.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.43.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.43.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.43.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.43.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.43.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.44.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.44.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.44.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.44.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.44.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.44.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.44.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.44.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.44.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.45.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.45.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.45.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.45.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.45.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.45.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.45.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.45.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.45.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.46.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.46.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.46.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.46.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.46.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.46.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.46.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.46.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.46.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.47.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.47.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.47.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.47.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.47.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.47.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.47.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.47.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.47.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.48.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.48.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.48.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.48.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.48.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.48.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.48.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.48.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.48.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.49.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.49.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.49.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.49.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.49.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.49.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.49.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.49.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.49.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.5.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.5.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.5.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.5.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.5.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.5.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.5.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.5.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.5.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.50.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.50.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.50.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.50.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.50.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.50.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.50.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.50.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.50.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.51.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.51.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.51.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.51.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.51.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.51.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.51.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.51.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.51.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.52.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.52.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.52.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.52.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.52.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.52.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.52.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.52.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.52.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.53.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.53.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.53.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.53.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.53.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.53.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.53.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.53.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.53.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.54.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.54.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.54.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.54.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.54.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.54.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.54.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.54.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.54.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.55.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.55.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.55.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.55.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.55.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.55.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.55.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.55.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.55.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.56.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.56.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.56.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.56.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.56.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.56.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.56.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.56.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.56.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.57.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.57.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.57.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.57.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.57.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.57.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.57.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.57.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.57.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.58.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.58.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.58.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.58.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.58.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.58.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.58.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.58.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.58.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.59.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.59.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.59.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.59.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.59.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.59.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.59.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.59.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.59.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.6.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.6.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.6.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.6.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.6.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.6.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.6.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.6.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.6.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.60.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.60.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.60.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.60.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.60.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.60.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.60.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.60.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.60.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.61.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.61.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.61.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.61.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.61.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.61.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.61.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.61.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.61.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.62.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.62.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.62.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.62.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.62.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.62.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.62.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.62.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.62.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.63.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.63.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.63.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.63.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.63.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.63.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.63.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.63.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.63.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.64.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.64.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.64.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.64.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.64.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.64.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.64.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.64.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.64.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.65.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.65.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.65.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.65.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.65.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.65.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.65.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.65.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.65.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.66.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.66.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.66.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.66.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.66.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.66.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.66.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.66.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.66.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.67.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.67.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.67.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.67.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.67.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.67.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.67.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.67.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.67.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.68.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.68.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.68.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.68.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.68.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.68.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.68.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.68.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.68.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.69.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.69.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.69.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.69.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.69.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.69.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.69.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.69.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.69.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.7.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.7.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.7.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.7.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.7.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.7.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.7.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.7.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.7.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.70.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.70.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.70.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.70.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.70.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.70.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.70.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.70.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.70.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.71.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.71.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.71.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.71.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.71.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.71.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.71.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.71.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.71.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.72.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.72.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.72.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.72.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.72.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.72.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.72.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.72.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.72.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.73.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.73.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.73.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.73.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.73.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.73.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.73.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.73.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.73.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.74.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.74.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.74.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.74.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.74.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.74.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.74.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.74.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.74.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.75.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.75.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.75.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.75.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.75.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.75.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.75.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.75.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.75.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.76.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.76.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.76.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.76.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.76.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.76.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.76.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.76.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.76.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.77.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.77.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.77.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.77.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.77.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.77.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.77.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.77.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.77.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.78.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.78.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.78.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.78.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.78.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.78.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.78.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.78.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.78.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.79.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.79.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.79.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.79.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.79.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.79.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.79.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.79.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.79.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.8.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.8.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.8.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.8.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.8.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.8.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.8.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.8.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.8.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.80.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.80.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.80.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.80.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.80.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.80.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.80.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.80.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.80.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.81.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.81.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.81.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.81.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.81.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.81.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.81.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.81.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.81.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.82.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.82.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.82.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.82.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.82.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.82.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.82.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.82.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.82.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.83.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.83.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.83.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.83.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.83.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.83.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.83.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.83.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.83.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.84.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.84.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.84.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.84.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.84.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.84.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.84.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.84.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.84.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.85.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.85.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.85.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.85.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.85.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.85.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.85.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.85.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.85.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.86.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.86.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.86.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.86.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.86.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.86.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.86.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.86.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.86.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.87.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.87.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.87.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.87.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.87.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.87.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.87.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.87.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.87.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.88.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.88.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.88.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.88.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.88.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.88.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.88.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.88.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.88.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.89.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.89.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.89.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.89.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.89.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.89.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.89.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.89.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.89.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.9.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.9.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.9.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.9.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.9.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.9.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.9.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.9.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.9.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.90.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.90.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.90.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.90.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.90.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.90.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.90.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.90.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.90.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.91.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.91.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.91.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.91.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.91.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.91.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.91.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.91.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.91.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.92.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.92.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.92.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.92.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.92.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.92.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.92.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.92.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.92.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.93.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.93.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.93.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.93.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.93.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.93.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.93.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.93.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.93.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.94.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.94.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.94.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.94.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.94.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.94.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.94.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.94.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.94.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.95.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.95.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.95.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.95.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.95.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.95.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.95.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.95.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.95.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.96.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.96.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.96.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.96.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.96.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.96.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.96.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.96.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.96.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.97.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.97.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.97.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.97.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.97.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.97.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.97.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.97.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.97.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.98.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.98.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.98.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.98.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.98.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.98.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.98.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.98.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.98.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.99.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.99.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.99.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.99.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.99.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.99.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.experts.99.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.mlp.gate.weight": "model-00003-of-00004.safetensors", - "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.43.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.100.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.100.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.100.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.100.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.100.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.100.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.100.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.100.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.100.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.101.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.101.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.101.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.101.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.101.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.101.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.101.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.101.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.101.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.102.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.102.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.102.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.102.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.102.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.102.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.102.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.102.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.102.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.103.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.103.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.103.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.103.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.103.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.103.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.103.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.103.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.103.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.104.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.104.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.104.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.104.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.104.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.104.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.104.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.104.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.104.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.105.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.105.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.105.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.105.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.105.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.105.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.105.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.105.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.105.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.106.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.106.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.106.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.106.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.106.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.106.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.106.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.106.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.106.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.107.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.107.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.107.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.107.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.107.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.107.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.107.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.107.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.107.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.108.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.108.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.108.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.108.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.108.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.108.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.108.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.108.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.108.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.109.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.109.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.109.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.109.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.109.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.109.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.109.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.109.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.109.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.110.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.110.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.110.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.110.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.110.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.110.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.110.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.110.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.110.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.111.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.111.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.111.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.111.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.111.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.111.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.111.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.111.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.111.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.112.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.112.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.112.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.112.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.112.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.112.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.112.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.112.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.112.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.113.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.113.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.113.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.113.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.113.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.113.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.113.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.113.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.113.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.114.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.114.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.114.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.114.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.114.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.114.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.114.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.114.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.114.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.115.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.115.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.115.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.115.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.115.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.115.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.115.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.115.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.115.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.116.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.116.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.116.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.116.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.116.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.116.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.116.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.116.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.116.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.117.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.117.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.117.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.117.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.117.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.117.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.117.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.117.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.117.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.118.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.118.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.118.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.118.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.118.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.118.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.118.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.118.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.118.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.119.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.119.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.119.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.119.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.119.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.119.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.119.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.119.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.119.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.120.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.120.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.120.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.120.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.120.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.120.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.120.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.120.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.120.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.121.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.121.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.121.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.121.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.121.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.121.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.121.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.121.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.121.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.122.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.122.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.122.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.122.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.122.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.122.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.122.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.122.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.122.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.123.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.123.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.123.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.123.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.123.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.123.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.123.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.123.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.123.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.124.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.124.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.124.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.124.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.124.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.124.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.124.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.124.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.124.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.125.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.125.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.125.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.125.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.125.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.125.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.125.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.125.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.125.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.126.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.126.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.126.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.126.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.126.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.126.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.126.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.126.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.126.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.127.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.127.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.127.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.127.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.127.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.127.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.127.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.127.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.127.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.64.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.64.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.64.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.64.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.64.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.64.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.64.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.64.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.64.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.65.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.65.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.65.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.65.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.65.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.65.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.65.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.65.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.65.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.66.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.66.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.66.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.66.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.66.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.66.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.66.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.66.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.66.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.67.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.67.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.67.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.67.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.67.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.67.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.67.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.67.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.67.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.68.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.68.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.68.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.68.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.68.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.68.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.68.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.68.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.68.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.69.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.69.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.69.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.69.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.69.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.69.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.69.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.69.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.69.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.70.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.70.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.70.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.70.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.70.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.70.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.70.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.70.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.70.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.71.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.71.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.71.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.71.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.71.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.71.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.71.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.71.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.71.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.72.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.72.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.72.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.72.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.72.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.72.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.72.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.72.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.72.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.73.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.73.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.73.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.73.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.73.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.73.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.73.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.73.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.73.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.74.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.74.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.74.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.74.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.74.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.74.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.74.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.74.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.74.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.75.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.75.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.75.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.75.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.75.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.75.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.75.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.75.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.75.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.76.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.76.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.76.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.76.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.76.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.76.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.76.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.76.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.76.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.77.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.77.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.77.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.77.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.77.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.77.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.77.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.77.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.77.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.78.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.78.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.78.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.78.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.78.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.78.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.78.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.78.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.78.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.79.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.79.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.79.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.79.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.79.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.79.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.79.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.79.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.79.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.80.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.80.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.80.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.80.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.80.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.80.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.80.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.80.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.80.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.81.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.81.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.81.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.81.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.81.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.81.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.81.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.81.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.81.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.82.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.82.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.82.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.82.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.82.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.82.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.82.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.82.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.82.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.83.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.83.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.83.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.83.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.83.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.83.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.83.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.83.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.83.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.84.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.84.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.84.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.84.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.84.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.84.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.84.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.84.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.84.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.85.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.85.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.85.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.85.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.85.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.85.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.85.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.85.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.85.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.86.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.86.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.86.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.86.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.86.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.86.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.86.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.86.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.86.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.87.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.87.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.87.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.87.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.87.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.87.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.87.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.87.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.87.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.88.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.88.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.88.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.88.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.88.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.88.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.88.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.88.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.88.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.89.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.89.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.89.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.89.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.89.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.89.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.89.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.89.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.89.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.90.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.90.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.90.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.90.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.90.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.90.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.90.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.90.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.90.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.91.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.91.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.91.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.91.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.91.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.91.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.91.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.91.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.91.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.92.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.92.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.92.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.92.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.92.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.92.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.92.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.92.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.92.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.93.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.93.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.93.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.93.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.93.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.93.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.93.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.93.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.93.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.94.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.94.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.94.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.94.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.94.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.94.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.94.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.94.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.94.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.95.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.95.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.95.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.95.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.95.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.95.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.95.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.95.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.95.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.96.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.96.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.96.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.96.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.96.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.96.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.96.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.96.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.96.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.97.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.97.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.97.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.97.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.97.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.97.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.97.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.97.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.97.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.98.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.98.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.98.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.98.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.98.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.98.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.98.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.98.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.98.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.99.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.99.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.99.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.99.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.99.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.99.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.99.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.99.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.experts.99.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.gate.weight": "model-00004-of-00004.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.100.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.100.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.100.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.100.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.100.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.100.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.100.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.100.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.100.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.101.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.101.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.101.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.101.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.101.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.101.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.101.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.101.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.101.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.102.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.102.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.102.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.102.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.102.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.102.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.102.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.102.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.102.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.103.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.103.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.103.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.103.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.103.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.103.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.103.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.103.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.103.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.104.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.104.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.104.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.104.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.104.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.104.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.104.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.104.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.104.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.105.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.105.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.105.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.105.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.105.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.105.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.105.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.105.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.105.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.106.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.106.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.106.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.106.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.106.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.106.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.106.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.106.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.106.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.107.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.107.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.107.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.107.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.107.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.107.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.107.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.107.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.107.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.108.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.108.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.108.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.108.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.108.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.108.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.108.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.108.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.108.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.109.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.109.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.109.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.109.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.109.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.109.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.109.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.109.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.109.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.110.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.110.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.110.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.110.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.110.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.110.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.110.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.110.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.110.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.111.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.111.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.111.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.111.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.111.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.111.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.111.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.111.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.111.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.112.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.112.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.112.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.112.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.112.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.112.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.112.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.112.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.112.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.113.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.113.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.113.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.113.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.113.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.113.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.113.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.113.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.113.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.114.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.114.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.114.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.114.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.114.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.114.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.114.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.114.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.114.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.115.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.115.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.115.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.115.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.115.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.115.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.115.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.115.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.115.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.116.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.116.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.116.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.116.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.116.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.116.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.116.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.116.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.116.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.117.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.117.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.117.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.117.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.117.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.117.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.117.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.117.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.117.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.118.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.118.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.118.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.118.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.118.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.118.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.118.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.118.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.118.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.119.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.119.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.119.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.119.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.119.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.119.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.119.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.119.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.119.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.120.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.120.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.120.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.120.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.120.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.120.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.120.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.120.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.120.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.121.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.121.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.121.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.121.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.121.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.121.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.121.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.121.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.121.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.122.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.122.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.122.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.122.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.122.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.122.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.122.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.122.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.122.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.123.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.123.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.123.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.123.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.123.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.123.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.123.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.123.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.123.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.124.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.124.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.124.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.124.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.124.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.124.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.124.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.124.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.124.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.125.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.125.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.125.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.125.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.125.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.125.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.125.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.125.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.125.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.126.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.126.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.126.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.126.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.126.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.126.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.126.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.126.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.126.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.127.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.127.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.127.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.127.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.127.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.127.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.127.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.127.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.127.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.64.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.64.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.64.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.64.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.64.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.64.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.64.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.64.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.64.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.65.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.65.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.65.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.65.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.65.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.65.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.65.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.65.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.65.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.66.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.66.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.66.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.66.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.66.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.66.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.66.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.66.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.66.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.67.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.67.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.67.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.67.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.67.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.67.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.67.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.67.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.67.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.68.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.68.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.68.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.68.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.68.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.68.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.68.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.68.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.68.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.69.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.69.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.69.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.69.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.69.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.69.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.69.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.69.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.69.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.70.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.70.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.70.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.70.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.70.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.70.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.70.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.70.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.70.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.71.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.71.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.71.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.71.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.71.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.71.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.71.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.71.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.71.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.72.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.72.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.72.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.72.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.72.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.72.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.72.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.72.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.72.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.73.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.73.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.73.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.73.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.73.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.73.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.73.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.73.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.73.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.74.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.74.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.74.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.74.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.74.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.74.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.74.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.74.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.74.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.75.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.75.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.75.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.75.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.75.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.75.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.75.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.75.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.75.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.76.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.76.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.76.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.76.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.76.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.76.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.76.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.76.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.76.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.77.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.77.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.77.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.77.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.77.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.77.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.77.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.77.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.77.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.78.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.78.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.78.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.78.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.78.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.78.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.78.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.78.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.78.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.79.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.79.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.79.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.79.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.79.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.79.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.79.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.79.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.79.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.80.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.80.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.80.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.80.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.80.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.80.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.80.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.80.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.80.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.81.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.81.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.81.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.81.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.81.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.81.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.81.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.81.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.81.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.82.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.82.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.82.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.82.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.82.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.82.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.82.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.82.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.82.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.83.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.83.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.83.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.83.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.83.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.83.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.83.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.83.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.83.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.84.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.84.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.84.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.84.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.84.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.84.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.84.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.84.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.84.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.85.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.85.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.85.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.85.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.85.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.85.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.85.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.85.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.85.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.86.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.86.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.86.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.86.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.86.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.86.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.86.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.86.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.86.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.87.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.87.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.87.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.87.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.87.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.87.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.87.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.87.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.87.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.88.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.88.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.88.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.88.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.88.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.88.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.88.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.88.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.88.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.89.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.89.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.89.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.89.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.89.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.89.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.89.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.89.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.89.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.90.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.90.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.90.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.90.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.90.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.90.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.90.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.90.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.90.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.91.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.91.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.91.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.91.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.91.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.91.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.91.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.91.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.91.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.92.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.92.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.92.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.92.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.92.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.92.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.92.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.92.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.92.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.93.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.93.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.93.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.93.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.93.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.93.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.93.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.93.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.93.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.94.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.94.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.94.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.94.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.94.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.94.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.94.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.94.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.94.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.95.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.95.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.95.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.95.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.95.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.95.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.95.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.95.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.95.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.96.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.96.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.96.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.96.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.96.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.96.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.96.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.96.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.96.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.97.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.97.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.97.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.97.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.97.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.97.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.97.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.97.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.97.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.98.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.98.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.98.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.98.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.98.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.98.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.98.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.98.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.98.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.99.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.99.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.99.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.99.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.99.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.99.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.99.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.99.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.experts.99.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.gate.weight": "model-00004-of-00004.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.100.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.100.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.100.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.100.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.100.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.100.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.100.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.100.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.100.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.101.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.101.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.101.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.101.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.101.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.101.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.101.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.101.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.101.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.102.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.102.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.102.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.102.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.102.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.102.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.102.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.102.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.102.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.103.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.103.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.103.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.103.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.103.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.103.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.103.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.103.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.103.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.104.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.104.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.104.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.104.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.104.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.104.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.104.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.104.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.104.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.105.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.105.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.105.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.105.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.105.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.105.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.105.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.105.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.105.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.106.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.106.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.106.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.106.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.106.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.106.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.106.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.106.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.106.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.107.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.107.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.107.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.107.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.107.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.107.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.107.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.107.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.107.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.108.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.108.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.108.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.108.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.108.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.108.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.108.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.108.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.108.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.109.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.109.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.109.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.109.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.109.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.109.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.109.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.109.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.109.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.110.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.110.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.110.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.110.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.110.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.110.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.110.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.110.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.110.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.111.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.111.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.111.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.111.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.111.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.111.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.111.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.111.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.111.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.112.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.112.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.112.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.112.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.112.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.112.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.112.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.112.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.112.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.113.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.113.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.113.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.113.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.113.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.113.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.113.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.113.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.113.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.114.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.114.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.114.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.114.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.114.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.114.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.114.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.114.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.114.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.115.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.115.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.115.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.115.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.115.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.115.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.115.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.115.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.115.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.116.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.116.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.116.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.116.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.116.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.116.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.116.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.116.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.116.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.117.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.117.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.117.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.117.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.117.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.117.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.117.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.117.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.117.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.118.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.118.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.118.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.118.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.118.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.118.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.118.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.118.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.118.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.119.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.119.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.119.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.119.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.119.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.119.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.119.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.119.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.119.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.120.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.120.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.120.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.120.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.120.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.120.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.120.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.120.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.120.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.121.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.121.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.121.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.121.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.121.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.121.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.121.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.121.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.121.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.122.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.122.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.122.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.122.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.122.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.122.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.122.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.122.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.122.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.123.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.123.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.123.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.123.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.123.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.123.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.123.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.123.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.123.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.124.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.124.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.124.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.124.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.124.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.124.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.124.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.124.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.124.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.125.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.125.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.125.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.125.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.125.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.125.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.125.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.125.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.125.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.126.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.126.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.126.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.126.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.126.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.126.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.126.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.126.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.126.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.127.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.127.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.127.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.127.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.127.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.127.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.127.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.127.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.127.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.64.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.64.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.64.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.64.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.64.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.64.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.64.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.64.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.64.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.65.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.65.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.65.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.65.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.65.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.65.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.65.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.65.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.65.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.66.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.66.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.66.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.66.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.66.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.66.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.66.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.66.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.66.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.67.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.67.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.67.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.67.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.67.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.67.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.67.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.67.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.67.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.68.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.68.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.68.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.68.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.68.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.68.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.68.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.68.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.68.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.69.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.69.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.69.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.69.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.69.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.69.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.69.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.69.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.69.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.70.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.70.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.70.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.70.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.70.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.70.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.70.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.70.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.70.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.71.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.71.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.71.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.71.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.71.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.71.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.71.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.71.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.71.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.72.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.72.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.72.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.72.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.72.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.72.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.72.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.72.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.72.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.73.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.73.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.73.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.73.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.73.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.73.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.73.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.73.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.73.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.74.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.74.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.74.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.74.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.74.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.74.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.74.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.74.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.74.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.75.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.75.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.75.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.75.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.75.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.75.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.75.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.75.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.75.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.76.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.76.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.76.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.76.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.76.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.76.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.76.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.76.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.76.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.77.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.77.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.77.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.77.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.77.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.77.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.77.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.77.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.77.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.78.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.78.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.78.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.78.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.78.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.78.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.78.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.78.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.78.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.79.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.79.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.79.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.79.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.79.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.79.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.79.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.79.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.79.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.80.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.80.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.80.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.80.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.80.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.80.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.80.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.80.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.80.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.81.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.81.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.81.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.81.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.81.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.81.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.81.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.81.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.81.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.82.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.82.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.82.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.82.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.82.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.82.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.82.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.82.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.82.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.83.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.83.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.83.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.83.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.83.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.83.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.83.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.83.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.83.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.84.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.84.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.84.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.84.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.84.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.84.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.84.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.84.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.84.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.85.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.85.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.85.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.85.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.85.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.85.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.85.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.85.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.85.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.86.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.86.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.86.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.86.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.86.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.86.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.86.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.86.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.86.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.87.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.87.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.87.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.87.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.87.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.87.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.87.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.87.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.87.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.88.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.88.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.88.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.88.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.88.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.88.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.88.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.88.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.88.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.89.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.89.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.89.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.89.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.89.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.89.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.89.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.89.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.89.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.90.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.90.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.90.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.90.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.90.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.90.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.90.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.90.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.90.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.91.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.91.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.91.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.91.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.91.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.91.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.91.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.91.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.91.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.92.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.92.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.92.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.92.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.92.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.92.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.92.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.92.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.92.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.93.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.93.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.93.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.93.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.93.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.93.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.93.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.93.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.93.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.94.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.94.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.94.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.94.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.94.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.94.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.94.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.94.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.94.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.95.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.95.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.95.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.95.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.95.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.95.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.95.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.95.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.95.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.96.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.96.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.96.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.96.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.96.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.96.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.96.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.96.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.96.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.97.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.97.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.97.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.97.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.97.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.97.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.97.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.97.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.97.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.98.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.98.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.98.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.98.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.98.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.98.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.98.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.98.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.98.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.99.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.99.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.99.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.99.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.99.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.99.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.99.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.99.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.experts.99.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.gate.weight": "model-00004-of-00004.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", "model.layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.44.mlp.experts.0.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.0.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.0.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.0.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.0.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.0.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.0.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.0.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.0.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.1.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.1.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.1.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.1.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.1.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.1.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.1.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.1.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.1.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.10.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.10.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.10.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.10.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.10.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.10.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.10.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.10.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.10.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight_shape": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.100.down_proj.weight_packed": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.100.down_proj.weight_scale": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.100.down_proj.weight_shape": "model-00004-of-00004.safetensors", @@ -45715,15 +45715,15 @@ "model.layers.44.mlp.experts.109.up_proj.weight_packed": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.109.up_proj.weight_scale": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.109.up_proj.weight_shape": "model-00004-of-00004.safetensors", - "model.layers.44.mlp.experts.11.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.11.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.11.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.11.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.11.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.11.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.11.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.11.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.11.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight_shape": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.110.down_proj.weight_packed": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.110.down_proj.weight_scale": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.110.down_proj.weight_shape": "model-00004-of-00004.safetensors", @@ -45814,15 +45814,15 @@ "model.layers.44.mlp.experts.119.up_proj.weight_packed": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.119.up_proj.weight_scale": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.119.up_proj.weight_shape": "model-00004-of-00004.safetensors", - "model.layers.44.mlp.experts.12.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.12.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.12.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.12.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.12.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.12.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.12.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.12.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.12.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight_shape": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.120.down_proj.weight_packed": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.120.down_proj.weight_scale": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.120.down_proj.weight_shape": "model-00004-of-00004.safetensors", @@ -45895,741 +45895,741 @@ "model.layers.44.mlp.experts.127.up_proj.weight_packed": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.127.up_proj.weight_scale": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.127.up_proj.weight_shape": "model-00004-of-00004.safetensors", - "model.layers.44.mlp.experts.13.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.13.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.13.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.13.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.13.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.13.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.13.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.13.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.13.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.14.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.14.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.14.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.14.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.14.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.14.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.14.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.14.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.14.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.15.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.15.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.15.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.15.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.15.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.15.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.15.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.15.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.15.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.16.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.16.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.16.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.16.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.16.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.16.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.16.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.16.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.16.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.17.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.17.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.17.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.17.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.17.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.17.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.17.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.17.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.17.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.18.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.18.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.18.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.18.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.18.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.18.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.18.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.18.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.18.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.19.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.19.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.19.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.19.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.19.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.19.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.19.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.19.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.19.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.2.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.2.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.2.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.2.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.2.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.2.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.2.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.2.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.2.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.20.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.20.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.20.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.20.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.20.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.20.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.20.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.20.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.20.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.21.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.21.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.21.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.21.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.21.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.21.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.21.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.21.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.21.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.22.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.22.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.22.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.22.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.22.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.22.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.22.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.22.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.22.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.23.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.23.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.23.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.23.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.23.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.23.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.23.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.23.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.23.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.24.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.24.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.24.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.24.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.24.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.24.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.24.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.24.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.24.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.25.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.25.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.25.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.25.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.25.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.25.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.25.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.25.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.25.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.26.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.26.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.26.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.26.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.26.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.26.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.26.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.26.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.26.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.27.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.27.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.27.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.27.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.27.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.27.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.27.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.27.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.27.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.28.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.28.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.28.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.28.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.28.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.28.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.28.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.28.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.28.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.29.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.29.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.29.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.29.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.29.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.29.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.29.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.29.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.29.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.3.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.3.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.3.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.3.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.3.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.3.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.3.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.3.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.3.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.30.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.30.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.30.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.30.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.30.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.30.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.30.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.30.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.30.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.31.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.31.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.31.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.31.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.31.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.31.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.31.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.31.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.31.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.32.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.32.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.32.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.32.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.32.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.32.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.32.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.32.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.32.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.33.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.33.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.33.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.33.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.33.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.33.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.33.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.33.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.33.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.34.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.34.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.34.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.34.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.34.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.34.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.34.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.34.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.34.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.35.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.35.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.35.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.35.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.35.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.35.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.35.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.35.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.35.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.36.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.36.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.36.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.36.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.36.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.36.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.36.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.36.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.36.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.37.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.37.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.37.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.37.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.37.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.37.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.37.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.37.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.37.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.38.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.38.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.38.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.38.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.38.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.38.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.38.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.38.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.38.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.39.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.39.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.39.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.39.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.39.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.39.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.39.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.39.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.39.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.4.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.4.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.4.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.4.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.4.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.4.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.4.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.4.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.4.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.40.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.40.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.40.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.40.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.40.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.40.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.40.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.40.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.40.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.41.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.41.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.41.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.41.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.41.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.41.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.41.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.41.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.41.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.42.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.42.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.42.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.42.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.42.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.42.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.42.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.42.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.42.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.43.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.43.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.43.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.43.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.43.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.43.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.43.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.43.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.43.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.44.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.44.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.44.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.44.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.44.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.44.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.44.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.44.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.44.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.45.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.45.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.45.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.45.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.45.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.45.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.45.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.45.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.45.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.46.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.46.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.46.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.46.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.46.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.46.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.46.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.46.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.46.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.47.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.47.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.47.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.47.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.47.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.47.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.47.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.47.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.47.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.48.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.48.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.48.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.48.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.48.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.48.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.48.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.48.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.48.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.49.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.49.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.49.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.49.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.49.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.49.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.49.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.49.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.49.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.5.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.5.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.5.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.5.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.5.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.5.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.5.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.5.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.5.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.50.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.50.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.50.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.50.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.50.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.50.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.50.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.50.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.50.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.51.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.51.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.51.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.51.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.51.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.51.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.51.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.51.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.51.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.52.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.52.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.52.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.52.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.52.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.52.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.52.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.52.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.52.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.53.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.53.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.53.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.53.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.53.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.53.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.53.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.53.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.53.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.54.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.54.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.54.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.54.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.54.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.54.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.54.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.54.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.54.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.55.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.55.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.55.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.55.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.55.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.55.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.55.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.55.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.55.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.56.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.56.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.56.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.56.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.56.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.56.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.56.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.56.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.56.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.57.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.57.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.57.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.57.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.57.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.57.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.57.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.57.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.57.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.58.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.58.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.58.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.58.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.58.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.58.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.58.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.58.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.58.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.59.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.59.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.59.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.59.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.59.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.59.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.59.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.59.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.59.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.6.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.6.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.6.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.6.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.6.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.6.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.6.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.6.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.6.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.60.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.60.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.60.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.60.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.60.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.60.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.60.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.60.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.60.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.61.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.61.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.61.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.61.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.61.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.61.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.61.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.61.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.61.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.62.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.62.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.62.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.62.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.62.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.62.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.62.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.62.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.62.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.63.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.63.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.63.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.63.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.63.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.63.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.63.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.63.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.63.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.64.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.64.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.64.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.64.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.64.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.64.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.64.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.64.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.64.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.65.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.65.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.65.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.65.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.65.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.65.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.65.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.65.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.65.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.66.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.66.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.66.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.66.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.66.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.66.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.66.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.66.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.66.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.67.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.67.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.67.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.67.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.67.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.67.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.67.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.67.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.67.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.68.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.68.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.68.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.68.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.68.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.68.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.68.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.68.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.68.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.69.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.69.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.69.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.69.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.69.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.69.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.69.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.69.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.69.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.7.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.7.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.7.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.7.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.7.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.7.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.7.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.7.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.7.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.70.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.70.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.70.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.70.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.70.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.70.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.70.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.70.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.70.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.71.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.71.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.71.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.71.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.71.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.71.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.71.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.71.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.71.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.72.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.72.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.72.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.72.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.72.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.72.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.72.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.72.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.72.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.73.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.73.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.73.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.73.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.73.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.73.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.73.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.73.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.73.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.74.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.74.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.74.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.74.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.74.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.74.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.74.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.74.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.74.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.75.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.75.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.75.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.75.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.75.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.75.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.75.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.75.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.75.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.76.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.76.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.76.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.76.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.76.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.76.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.76.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.76.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.76.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.77.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.77.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.77.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.77.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.77.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.77.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.77.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.77.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.77.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.78.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.78.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.78.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.78.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.78.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.78.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.78.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.78.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.78.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.79.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.79.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.79.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.79.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.79.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.79.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.79.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.79.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.79.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.8.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.8.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.8.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.8.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.8.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.8.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.8.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.8.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.8.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.80.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.80.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.80.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.80.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.80.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.80.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.80.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.80.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.80.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.81.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.81.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.81.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.81.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.81.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.81.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.81.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.81.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.81.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.82.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.82.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.82.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.82.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.82.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.82.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.82.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.82.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.82.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.83.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.83.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.83.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.83.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.83.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.83.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.83.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.83.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.83.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.84.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.84.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.84.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.84.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.84.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.84.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.84.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.84.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.84.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.85.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.85.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.85.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.85.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.85.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.85.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.85.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.85.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.85.up_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.86.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.86.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.86.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.86.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.86.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.86.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.86.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.86.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.86.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.64.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.64.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.64.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.64.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.64.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.64.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.64.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.64.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.64.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.65.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.65.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.65.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.65.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.65.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.65.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.65.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.65.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.65.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.66.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.66.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.66.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.66.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.66.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.66.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.66.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.66.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.66.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.67.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.67.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.67.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.67.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.67.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.67.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.67.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.67.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.67.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.68.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.68.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.68.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.68.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.68.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.68.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.68.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.68.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.68.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.69.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.69.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.69.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.69.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.69.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.69.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.69.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.69.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.69.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.70.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.70.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.70.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.70.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.70.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.70.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.70.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.70.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.70.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.71.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.71.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.71.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.71.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.71.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.71.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.71.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.71.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.71.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.72.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.72.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.72.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.72.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.72.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.72.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.72.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.72.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.72.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.73.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.73.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.73.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.73.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.73.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.73.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.73.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.73.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.73.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.74.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.74.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.74.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.74.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.74.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.74.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.74.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.74.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.74.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.75.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.75.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.75.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.75.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.75.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.75.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.75.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.75.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.75.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.76.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.76.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.76.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.76.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.76.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.76.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.76.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.76.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.76.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.77.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.77.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.77.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.77.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.77.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.77.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.77.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.77.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.77.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.78.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.78.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.78.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.78.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.78.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.78.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.78.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.78.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.78.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.79.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.79.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.79.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.79.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.79.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.79.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.79.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.79.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.79.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.80.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.80.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.80.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.80.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.80.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.80.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.80.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.80.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.80.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.81.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.81.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.81.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.81.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.81.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.81.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.81.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.81.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.81.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.82.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.82.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.82.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.82.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.82.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.82.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.82.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.82.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.82.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.83.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.83.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.83.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.83.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.83.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.83.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.83.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.83.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.83.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.84.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.84.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.84.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.84.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.84.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.84.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.84.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.84.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.84.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.85.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.85.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.85.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.85.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.85.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.85.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.85.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.85.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.85.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.86.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.86.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.86.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.86.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.86.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.86.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.86.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.86.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.86.up_proj.weight_shape": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.87.down_proj.weight_packed": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.87.down_proj.weight_scale": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.87.down_proj.weight_shape": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.87.gate_proj.weight_packed": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.87.gate_proj.weight_scale": "model-00004-of-00004.safetensors", - "model.layers.44.mlp.experts.87.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.experts.87.gate_proj.weight_shape": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.87.up_proj.weight_packed": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.87.up_proj.weight_scale": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.87.up_proj.weight_shape": "model-00004-of-00004.safetensors", @@ -46651,15 +46651,15 @@ "model.layers.44.mlp.experts.89.up_proj.weight_packed": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.89.up_proj.weight_scale": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.89.up_proj.weight_shape": "model-00004-of-00004.safetensors", - "model.layers.44.mlp.experts.9.down_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.9.down_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.9.down_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.9.gate_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.9.gate_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.9.gate_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.9.up_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.9.up_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.mlp.experts.9.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight_shape": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.90.down_proj.weight_packed": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.90.down_proj.weight_scale": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.90.down_proj.weight_shape": "model-00004-of-00004.safetensors", @@ -46750,22 +46750,22 @@ "model.layers.44.mlp.experts.99.up_proj.weight_packed": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.99.up_proj.weight_scale": "model-00004-of-00004.safetensors", "model.layers.44.mlp.experts.99.up_proj.weight_shape": "model-00004-of-00004.safetensors", - "model.layers.44.mlp.gate.weight": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.gate.weight": "model-00004-of-00004.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.44.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", - "model.layers.44.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", - "model.layers.44.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", - "model.layers.44.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", - "model.layers.44.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", - "model.layers.44.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", "model.layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.45.mlp.experts.0.down_proj.weight_packed": "model-00004-of-00004.safetensors", "model.layers.45.mlp.experts.0.down_proj.weight_scale": "model-00004-of-00004.safetensors",