model.safetensors.index.json

{
  "metadata": {
    "total_size": 5791289344
  },
  "weight_map": {
    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.gate.wg.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.shared_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.shared_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.shared_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.key_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.query_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.gate.wg.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.shared_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.shared_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.shared_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.key_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.query_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.gate.wg.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.shared_mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.shared_mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.shared_mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.key_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.query_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.experts.0.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.experts.0.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.experts.1.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.experts.1.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.experts.2.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.experts.2.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.experts.3.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.experts.3.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.gate.wg.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.shared_mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.shared_mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.mlp.shared_mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.self_attn.key_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.self_attn.query_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.norm.weight": "model-00002-of-00002.safetensors"
  }
}