| { |
| "metadata": { |
| "total_parameters": 3483006976, |
| "total_size": 13932027968 |
| }, |
| "weight_map": { |
| "lm_head.weight": "model-00003-of-00003.safetensors", |
| "model.embed_tokens.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.input_layernorm.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.0.input_layernorm.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.4.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.4.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.4.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.5.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.5.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.5.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.6.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.6.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.6.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.7.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.7.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.experts.7.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.router.classifier.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.router.e_score_correction_bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlps.0.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.0.mlps.0.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.0.mlps.0.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.0.mlps.1.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.0.mlps.1.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.0.mlps.1.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.0.post_attention_layernorm.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.0.post_attention_layernorm.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.0.self_attn.0.kv_a_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.0.kv_a_proj_with_mqa.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.0.kv_b_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.0.o_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.0.q_a_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.0.q_a_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.0.q_b_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.1.kv_a_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.1.kv_a_proj_with_mqa.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.1.kv_b_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.1.o_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.0.self_attn.1.q_a_layernorm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.1.q_a_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.1.q_b_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.input_layernorm.0.weight": "model-00003-of-00003.safetensors", |
| "model.layers.1.input_layernorm.1.weight": "model-00003-of-00003.safetensors", |
| "model.layers.1.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.4.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.4.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.5.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.5.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.6.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.6.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.7.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.experts.7.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.router.classifier.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlp.router.e_score_correction_bias": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlps.0.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlps.0.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlps.0.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.mlps.1.down_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.1.mlps.1.gate_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.1.mlps.1.up_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.1.post_attention_layernorm.0.weight": "model-00003-of-00003.safetensors", |
| "model.layers.1.post_attention_layernorm.1.weight": "model-00003-of-00003.safetensors", |
| "model.layers.1.self_attn.0.kv_a_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.self_attn.0.kv_a_proj_with_mqa.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.self_attn.0.kv_b_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.self_attn.0.o_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.self_attn.0.q_a_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.self_attn.0.q_a_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.self_attn.0.q_b_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.self_attn.1.kv_a_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.self_attn.1.kv_a_proj_with_mqa.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.self_attn.1.kv_b_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.self_attn.1.o_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.self_attn.1.q_a_layernorm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.self_attn.1.q_a_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.1.self_attn.1.q_b_proj.weight": "model-00002-of-00003.safetensors", |
| "model.norm.weight": "model-00003-of-00003.safetensors" |
| } |
| } |
|
|
