model.safetensors.index.json

{
  "metadata": {
    "total_size": 10708875360
  },
  "weight_map": {
    "lm_head.weight": "model-00003-of-00003.safetensors",
    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.kv_a_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.kv_b_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.q_a_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.q_a_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.0.self_attn.q_b_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.kv_a_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.kv_b_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.q_a_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.q_a_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.1.self_attn.q_b_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.2.self_attn.kv_a_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.kv_b_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.q_a_layernorm.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.q_a_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.2.self_attn.q_b_proj.weight": "model-00001-of-00003.safetensors",
    "model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.4.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.4.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.5.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.5.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.6.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.6.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.7.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.experts.7.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.gate.e_score_correction_bias": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.gate.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.self_attn.kv_a_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.self_attn.kv_b_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.self_attn.q_a_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.self_attn.q_a_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.3.self_attn.q_b_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.4.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.4.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.5.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.5.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.6.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.6.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.7.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.experts.7.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.gate.e_score_correction_bias": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.gate.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.self_attn.kv_a_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.self_attn.kv_b_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.self_attn.q_a_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.self_attn.q_a_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.4.self_attn.q_b_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.4.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.4.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.5.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.5.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.6.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.6.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.7.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.experts.7.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.gate.e_score_correction_bias": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.gate.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.self_attn.kv_a_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.self_attn.kv_b_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.self_attn.q_a_layernorm.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.self_attn.q_a_proj.weight": "model-00002-of-00003.safetensors",
    "model.layers.5.self_attn.q_b_proj.weight": "model-00002-of-00003.safetensors",
    "model.norm.weight": "model-00002-of-00003.safetensors"
  }
}