| { | |
| "metadata": { | |
| "total_size": 19532673280 | |
| }, | |
| "weight_map": { | |
| "model.layers.0.self_attn.q_proj.weight": "model-1-of-35.safetensors", | |
| "model.layers.0.self_attn.k_proj.weight": "model-1-of-35.safetensors", | |
| "model.layers.0.self_attn.v_proj.weight": "model-1-of-35.safetensors", | |
| "model.layers.0.self_attn.o_proj.weight": "model-1-of-35.safetensors", | |
| "model.layers.0.self_attn.q_proj.bias": "model-1-of-35.safetensors", | |
| "model.layers.0.self_attn.k_proj.bias": "model-1-of-35.safetensors", | |
| "model.layers.0.self_attn.v_proj.bias": "model-1-of-35.safetensors", | |
| "model.layers.0.input_layernorm.weight": "model-1-of-35.safetensors", | |
| "model.layers.0.post_attention_layernorm.weight": "model-1-of-35.safetensors", | |
| "model.layers.0.mlp.gate_proj.weight": "model-1-of-35.safetensors", | |
| "model.layers.0.mlp.down_proj.weight": "model-1-of-35.safetensors", | |
| "model.layers.0.mlp.up_proj.weight": "model-1-of-35.safetensors", | |
| "model.layers.0.self_attn.rotary_emb.inv_freq": "model-1-of-35.safetensors", | |
| "model.layers.1.self_attn.q_proj.weight": "model-2-of-35.safetensors", | |
| "model.layers.1.self_attn.k_proj.weight": "model-2-of-35.safetensors", | |
| "model.layers.1.self_attn.v_proj.weight": "model-2-of-35.safetensors", | |
| "model.layers.1.self_attn.o_proj.weight": "model-2-of-35.safetensors", | |
| "model.layers.1.self_attn.q_proj.bias": "model-2-of-35.safetensors", | |
| "model.layers.1.self_attn.k_proj.bias": "model-2-of-35.safetensors", | |
| "model.layers.1.self_attn.v_proj.bias": "model-2-of-35.safetensors", | |
| "model.layers.1.input_layernorm.weight": "model-2-of-35.safetensors", | |
| "model.layers.1.post_attention_layernorm.weight": "model-2-of-35.safetensors", | |
| "model.layers.1.mlp.gate_proj.weight": "model-2-of-35.safetensors", | |
| "model.layers.1.mlp.down_proj.weight": "model-2-of-35.safetensors", | |
| "model.layers.1.mlp.up_proj.weight": "model-2-of-35.safetensors", | |
| "model.layers.1.self_attn.rotary_emb.inv_freq": "model-2-of-35.safetensors", | |
| "model.layers.2.self_attn.q_proj.weight": "model-3-of-35.safetensors", | |
| "model.layers.2.self_attn.k_proj.weight": "model-3-of-35.safetensors", | |
| "model.layers.2.self_attn.v_proj.weight": "model-3-of-35.safetensors", | |
| "model.layers.2.self_attn.o_proj.weight": "model-3-of-35.safetensors", | |
| "model.layers.2.self_attn.q_proj.bias": "model-3-of-35.safetensors", | |
| "model.layers.2.self_attn.k_proj.bias": "model-3-of-35.safetensors", | |
| "model.layers.2.self_attn.v_proj.bias": "model-3-of-35.safetensors", | |
| "model.layers.2.input_layernorm.weight": "model-3-of-35.safetensors", | |
| "model.layers.2.post_attention_layernorm.weight": "model-3-of-35.safetensors", | |
| "model.layers.2.mlp.gate_proj.weight": "model-3-of-35.safetensors", | |
| "model.layers.2.mlp.down_proj.weight": "model-3-of-35.safetensors", | |
| "model.layers.2.mlp.up_proj.weight": "model-3-of-35.safetensors", | |
| "model.layers.2.self_attn.rotary_emb.inv_freq": "model-3-of-35.safetensors", | |
| "model.layers.3.self_attn.q_proj.weight": "model-4-of-35.safetensors", | |
| "model.layers.3.self_attn.k_proj.weight": "model-4-of-35.safetensors", | |
| "model.layers.3.self_attn.v_proj.weight": "model-4-of-35.safetensors", | |
| "model.layers.3.self_attn.o_proj.weight": "model-4-of-35.safetensors", | |
| "model.layers.3.self_attn.q_proj.bias": "model-4-of-35.safetensors", | |
| "model.layers.3.self_attn.k_proj.bias": "model-4-of-35.safetensors", | |
| "model.layers.3.self_attn.v_proj.bias": "model-4-of-35.safetensors", | |
| "model.layers.3.input_layernorm.weight": "model-4-of-35.safetensors", | |
| "model.layers.3.post_attention_layernorm.weight": "model-4-of-35.safetensors", | |
| "model.layers.3.mlp.gate_proj.weight": "model-4-of-35.safetensors", | |
| "model.layers.3.mlp.down_proj.weight": "model-4-of-35.safetensors", | |
| "model.layers.3.mlp.up_proj.weight": "model-4-of-35.safetensors", | |
| "model.layers.3.self_attn.rotary_emb.inv_freq": "model-4-of-35.safetensors", | |
| "model.layers.4.self_attn.q_proj.weight": "model-5-of-35.safetensors", | |
| "model.layers.4.self_attn.k_proj.weight": "model-5-of-35.safetensors", | |
| "model.layers.4.self_attn.v_proj.weight": "model-5-of-35.safetensors", | |
| "model.layers.4.self_attn.o_proj.weight": "model-5-of-35.safetensors", | |
| "model.layers.4.self_attn.q_proj.bias": "model-5-of-35.safetensors", | |
| "model.layers.4.self_attn.k_proj.bias": "model-5-of-35.safetensors", | |
| "model.layers.4.self_attn.v_proj.bias": "model-5-of-35.safetensors", | |
| "model.layers.4.input_layernorm.weight": "model-5-of-35.safetensors", | |
| "model.layers.4.post_attention_layernorm.weight": "model-5-of-35.safetensors", | |
| "model.layers.4.mlp.gate_proj.weight": "model-5-of-35.safetensors", | |
| "model.layers.4.mlp.down_proj.weight": "model-5-of-35.safetensors", | |
| "model.layers.4.mlp.up_proj.weight": "model-5-of-35.safetensors", | |
| "model.layers.4.self_attn.rotary_emb.inv_freq": "model-5-of-35.safetensors", | |
| "model.layers.5.self_attn.q_proj.weight": "model-6-of-35.safetensors", | |
| "model.layers.5.self_attn.k_proj.weight": "model-6-of-35.safetensors", | |
| "model.layers.5.self_attn.v_proj.weight": "model-6-of-35.safetensors", | |
| "model.layers.5.self_attn.o_proj.weight": "model-6-of-35.safetensors", | |
| "model.layers.5.self_attn.q_proj.bias": "model-6-of-35.safetensors", | |
| "model.layers.5.self_attn.k_proj.bias": "model-6-of-35.safetensors", | |
| "model.layers.5.self_attn.v_proj.bias": "model-6-of-35.safetensors", | |
| "model.layers.5.input_layernorm.weight": "model-6-of-35.safetensors", | |
| "model.layers.5.post_attention_layernorm.weight": "model-6-of-35.safetensors", | |
| "model.layers.5.mlp.gate_proj.weight": "model-6-of-35.safetensors", | |
| "model.layers.5.mlp.down_proj.weight": "model-6-of-35.safetensors", | |
| "model.layers.5.mlp.up_proj.weight": "model-6-of-35.safetensors", | |
| "model.layers.5.self_attn.rotary_emb.inv_freq": "model-6-of-35.safetensors", | |
| "model.layers.6.self_attn.q_proj.weight": "model-7-of-35.safetensors", | |
| "model.layers.6.self_attn.k_proj.weight": "model-7-of-35.safetensors", | |
| "model.layers.6.self_attn.v_proj.weight": "model-7-of-35.safetensors", | |
| "model.layers.6.self_attn.o_proj.weight": "model-7-of-35.safetensors", | |
| "model.layers.6.self_attn.q_proj.bias": "model-7-of-35.safetensors", | |
| "model.layers.6.self_attn.k_proj.bias": "model-7-of-35.safetensors", | |
| "model.layers.6.self_attn.v_proj.bias": "model-7-of-35.safetensors", | |
| "model.layers.6.input_layernorm.weight": "model-7-of-35.safetensors", | |
| "model.layers.6.post_attention_layernorm.weight": "model-7-of-35.safetensors", | |
| "model.layers.6.mlp.gate_proj.weight": "model-7-of-35.safetensors", | |
| "model.layers.6.mlp.down_proj.weight": "model-7-of-35.safetensors", | |
| "model.layers.6.mlp.up_proj.weight": "model-7-of-35.safetensors", | |
| "model.layers.6.self_attn.rotary_emb.inv_freq": "model-7-of-35.safetensors", | |
| "model.layers.7.self_attn.q_proj.weight": "model-8-of-35.safetensors", | |
| "model.layers.7.self_attn.k_proj.weight": "model-8-of-35.safetensors", | |
| "model.layers.7.self_attn.v_proj.weight": "model-8-of-35.safetensors", | |
| "model.layers.7.self_attn.o_proj.weight": "model-8-of-35.safetensors", | |
| "model.layers.7.self_attn.q_proj.bias": "model-8-of-35.safetensors", | |
| "model.layers.7.self_attn.k_proj.bias": "model-8-of-35.safetensors", | |
| "model.layers.7.self_attn.v_proj.bias": "model-8-of-35.safetensors", | |
| "model.layers.7.input_layernorm.weight": "model-8-of-35.safetensors", | |
| "model.layers.7.post_attention_layernorm.weight": "model-8-of-35.safetensors", | |
| "model.layers.7.mlp.gate_proj.weight": "model-8-of-35.safetensors", | |
| "model.layers.7.mlp.down_proj.weight": "model-8-of-35.safetensors", | |
| "model.layers.7.mlp.up_proj.weight": "model-8-of-35.safetensors", | |
| "model.layers.7.self_attn.rotary_emb.inv_freq": "model-8-of-35.safetensors", | |
| "model.layers.8.self_attn.q_proj.weight": "model-9-of-35.safetensors", | |
| "model.layers.8.self_attn.k_proj.weight": "model-9-of-35.safetensors", | |
| "model.layers.8.self_attn.v_proj.weight": "model-9-of-35.safetensors", | |
| "model.layers.8.self_attn.o_proj.weight": "model-9-of-35.safetensors", | |
| "model.layers.8.self_attn.q_proj.bias": "model-9-of-35.safetensors", | |
| "model.layers.8.self_attn.k_proj.bias": "model-9-of-35.safetensors", | |
| "model.layers.8.self_attn.v_proj.bias": "model-9-of-35.safetensors", | |
| "model.layers.8.input_layernorm.weight": "model-9-of-35.safetensors", | |
| "model.layers.8.post_attention_layernorm.weight": "model-9-of-35.safetensors", | |
| "model.layers.8.mlp.gate_proj.weight": "model-9-of-35.safetensors", | |
| "model.layers.8.mlp.down_proj.weight": "model-9-of-35.safetensors", | |
| "model.layers.8.mlp.up_proj.weight": "model-9-of-35.safetensors", | |
| "model.layers.8.self_attn.rotary_emb.inv_freq": "model-9-of-35.safetensors", | |
| "model.layers.9.self_attn.q_proj.weight": "model-10-of-35.safetensors", | |
| "model.layers.9.self_attn.k_proj.weight": "model-10-of-35.safetensors", | |
| "model.layers.9.self_attn.v_proj.weight": "model-10-of-35.safetensors", | |
| "model.layers.9.self_attn.o_proj.weight": "model-10-of-35.safetensors", | |
| "model.layers.9.self_attn.q_proj.bias": "model-10-of-35.safetensors", | |
| "model.layers.9.self_attn.k_proj.bias": "model-10-of-35.safetensors", | |
| "model.layers.9.self_attn.v_proj.bias": "model-10-of-35.safetensors", | |
| "model.layers.9.input_layernorm.weight": "model-10-of-35.safetensors", | |
| "model.layers.9.post_attention_layernorm.weight": "model-10-of-35.safetensors", | |
| "model.layers.9.mlp.gate_proj.weight": "model-10-of-35.safetensors", | |
| "model.layers.9.mlp.down_proj.weight": "model-10-of-35.safetensors", | |
| "model.layers.9.mlp.up_proj.weight": "model-10-of-35.safetensors", | |
| "model.layers.9.self_attn.rotary_emb.inv_freq": "model-10-of-35.safetensors", | |
| "model.layers.10.self_attn.q_proj.weight": "model-11-of-35.safetensors", | |
| "model.layers.10.self_attn.k_proj.weight": "model-11-of-35.safetensors", | |
| "model.layers.10.self_attn.v_proj.weight": "model-11-of-35.safetensors", | |
| "model.layers.10.self_attn.o_proj.weight": "model-11-of-35.safetensors", | |
| "model.layers.10.self_attn.q_proj.bias": "model-11-of-35.safetensors", | |
| "model.layers.10.self_attn.k_proj.bias": "model-11-of-35.safetensors", | |
| "model.layers.10.self_attn.v_proj.bias": "model-11-of-35.safetensors", | |
| "model.layers.10.input_layernorm.weight": "model-11-of-35.safetensors", | |
| "model.layers.10.post_attention_layernorm.weight": "model-11-of-35.safetensors", | |
| "model.layers.10.mlp.gate_proj.weight": "model-11-of-35.safetensors", | |
| "model.layers.10.mlp.down_proj.weight": "model-11-of-35.safetensors", | |
| "model.layers.10.mlp.up_proj.weight": "model-11-of-35.safetensors", | |
| "model.layers.10.self_attn.rotary_emb.inv_freq": "model-11-of-35.safetensors", | |
| "model.layers.11.self_attn.q_proj.weight": "model-12-of-35.safetensors", | |
| "model.layers.11.self_attn.k_proj.weight": "model-12-of-35.safetensors", | |
| "model.layers.11.self_attn.v_proj.weight": "model-12-of-35.safetensors", | |
| "model.layers.11.self_attn.o_proj.weight": "model-12-of-35.safetensors", | |
| "model.layers.11.self_attn.q_proj.bias": "model-12-of-35.safetensors", | |
| "model.layers.11.self_attn.k_proj.bias": "model-12-of-35.safetensors", | |
| "model.layers.11.self_attn.v_proj.bias": "model-12-of-35.safetensors", | |
| "model.layers.11.input_layernorm.weight": "model-12-of-35.safetensors", | |
| "model.layers.11.post_attention_layernorm.weight": "model-12-of-35.safetensors", | |
| "model.layers.11.mlp.gate_proj.weight": "model-12-of-35.safetensors", | |
| "model.layers.11.mlp.down_proj.weight": "model-12-of-35.safetensors", | |
| "model.layers.11.mlp.up_proj.weight": "model-12-of-35.safetensors", | |
| "model.layers.11.self_attn.rotary_emb.inv_freq": "model-12-of-35.safetensors", | |
| "model.layers.12.self_attn.q_proj.weight": "model-13-of-35.safetensors", | |
| "model.layers.12.self_attn.k_proj.weight": "model-13-of-35.safetensors", | |
| "model.layers.12.self_attn.v_proj.weight": "model-13-of-35.safetensors", | |
| "model.layers.12.self_attn.o_proj.weight": "model-13-of-35.safetensors", | |
| "model.layers.12.self_attn.q_proj.bias": "model-13-of-35.safetensors", | |
| "model.layers.12.self_attn.k_proj.bias": "model-13-of-35.safetensors", | |
| "model.layers.12.self_attn.v_proj.bias": "model-13-of-35.safetensors", | |
| "model.layers.12.input_layernorm.weight": "model-13-of-35.safetensors", | |
| "model.layers.12.post_attention_layernorm.weight": "model-13-of-35.safetensors", | |
| "model.layers.12.mlp.gate_proj.weight": "model-13-of-35.safetensors", | |
| "model.layers.12.mlp.down_proj.weight": "model-13-of-35.safetensors", | |
| "model.layers.12.mlp.up_proj.weight": "model-13-of-35.safetensors", | |
| "model.layers.12.self_attn.rotary_emb.inv_freq": "model-13-of-35.safetensors", | |
| "model.layers.13.self_attn.q_proj.weight": "model-14-of-35.safetensors", | |
| "model.layers.13.self_attn.k_proj.weight": "model-14-of-35.safetensors", | |
| "model.layers.13.self_attn.v_proj.weight": "model-14-of-35.safetensors", | |
| "model.layers.13.self_attn.o_proj.weight": "model-14-of-35.safetensors", | |
| "model.layers.13.self_attn.q_proj.bias": "model-14-of-35.safetensors", | |
| "model.layers.13.self_attn.k_proj.bias": "model-14-of-35.safetensors", | |
| "model.layers.13.self_attn.v_proj.bias": "model-14-of-35.safetensors", | |
| "model.layers.13.input_layernorm.weight": "model-14-of-35.safetensors", | |
| "model.layers.13.post_attention_layernorm.weight": "model-14-of-35.safetensors", | |
| "model.layers.13.mlp.gate_proj.weight": "model-14-of-35.safetensors", | |
| "model.layers.13.mlp.down_proj.weight": "model-14-of-35.safetensors", | |
| "model.layers.13.mlp.up_proj.weight": "model-14-of-35.safetensors", | |
| "model.layers.13.self_attn.rotary_emb.inv_freq": "model-14-of-35.safetensors", | |
| "model.layers.14.self_attn.q_proj.weight": "model-15-of-35.safetensors", | |
| "model.layers.14.self_attn.k_proj.weight": "model-15-of-35.safetensors", | |
| "model.layers.14.self_attn.v_proj.weight": "model-15-of-35.safetensors", | |
| "model.layers.14.self_attn.o_proj.weight": "model-15-of-35.safetensors", | |
| "model.layers.14.self_attn.q_proj.bias": "model-15-of-35.safetensors", | |
| "model.layers.14.self_attn.k_proj.bias": "model-15-of-35.safetensors", | |
| "model.layers.14.self_attn.v_proj.bias": "model-15-of-35.safetensors", | |
| "model.layers.14.input_layernorm.weight": "model-15-of-35.safetensors", | |
| "model.layers.14.post_attention_layernorm.weight": "model-15-of-35.safetensors", | |
| "model.layers.14.mlp.gate_proj.weight": "model-15-of-35.safetensors", | |
| "model.layers.14.mlp.down_proj.weight": "model-15-of-35.safetensors", | |
| "model.layers.14.mlp.up_proj.weight": "model-15-of-35.safetensors", | |
| "model.layers.14.self_attn.rotary_emb.inv_freq": "model-15-of-35.safetensors", | |
| "model.layers.15.self_attn.q_proj.weight": "model-16-of-35.safetensors", | |
| "model.layers.15.self_attn.k_proj.weight": "model-16-of-35.safetensors", | |
| "model.layers.15.self_attn.v_proj.weight": "model-16-of-35.safetensors", | |
| "model.layers.15.self_attn.o_proj.weight": "model-16-of-35.safetensors", | |
| "model.layers.15.self_attn.q_proj.bias": "model-16-of-35.safetensors", | |
| "model.layers.15.self_attn.k_proj.bias": "model-16-of-35.safetensors", | |
| "model.layers.15.self_attn.v_proj.bias": "model-16-of-35.safetensors", | |
| "model.layers.15.input_layernorm.weight": "model-16-of-35.safetensors", | |
| "model.layers.15.post_attention_layernorm.weight": "model-16-of-35.safetensors", | |
| "model.layers.15.mlp.gate_proj.weight": "model-16-of-35.safetensors", | |
| "model.layers.15.mlp.down_proj.weight": "model-16-of-35.safetensors", | |
| "model.layers.15.mlp.up_proj.weight": "model-16-of-35.safetensors", | |
| "model.layers.15.self_attn.rotary_emb.inv_freq": "model-16-of-35.safetensors", | |
| "model.layers.16.self_attn.q_proj.weight": "model-17-of-35.safetensors", | |
| "model.layers.16.self_attn.k_proj.weight": "model-17-of-35.safetensors", | |
| "model.layers.16.self_attn.v_proj.weight": "model-17-of-35.safetensors", | |
| "model.layers.16.self_attn.o_proj.weight": "model-17-of-35.safetensors", | |
| "model.layers.16.self_attn.q_proj.bias": "model-17-of-35.safetensors", | |
| "model.layers.16.self_attn.k_proj.bias": "model-17-of-35.safetensors", | |
| "model.layers.16.self_attn.v_proj.bias": "model-17-of-35.safetensors", | |
| "model.layers.16.input_layernorm.weight": "model-17-of-35.safetensors", | |
| "model.layers.16.post_attention_layernorm.weight": "model-17-of-35.safetensors", | |
| "model.layers.16.mlp.gate_proj.weight": "model-17-of-35.safetensors", | |
| "model.layers.16.mlp.down_proj.weight": "model-17-of-35.safetensors", | |
| "model.layers.16.mlp.up_proj.weight": "model-17-of-35.safetensors", | |
| "model.layers.16.self_attn.rotary_emb.inv_freq": "model-17-of-35.safetensors", | |
| "model.layers.17.self_attn.q_proj.weight": "model-18-of-35.safetensors", | |
| "model.layers.17.self_attn.k_proj.weight": "model-18-of-35.safetensors", | |
| "model.layers.17.self_attn.v_proj.weight": "model-18-of-35.safetensors", | |
| "model.layers.17.self_attn.o_proj.weight": "model-18-of-35.safetensors", | |
| "model.layers.17.self_attn.q_proj.bias": "model-18-of-35.safetensors", | |
| "model.layers.17.self_attn.k_proj.bias": "model-18-of-35.safetensors", | |
| "model.layers.17.self_attn.v_proj.bias": "model-18-of-35.safetensors", | |
| "model.layers.17.input_layernorm.weight": "model-18-of-35.safetensors", | |
| "model.layers.17.post_attention_layernorm.weight": "model-18-of-35.safetensors", | |
| "model.layers.17.mlp.gate_proj.weight": "model-18-of-35.safetensors", | |
| "model.layers.17.mlp.down_proj.weight": "model-18-of-35.safetensors", | |
| "model.layers.17.mlp.up_proj.weight": "model-18-of-35.safetensors", | |
| "model.layers.17.self_attn.rotary_emb.inv_freq": "model-18-of-35.safetensors", | |
| "model.layers.18.self_attn.q_proj.weight": "model-19-of-35.safetensors", | |
| "model.layers.18.self_attn.k_proj.weight": "model-19-of-35.safetensors", | |
| "model.layers.18.self_attn.v_proj.weight": "model-19-of-35.safetensors", | |
| "model.layers.18.self_attn.o_proj.weight": "model-19-of-35.safetensors", | |
| "model.layers.18.self_attn.q_proj.bias": "model-19-of-35.safetensors", | |
| "model.layers.18.self_attn.k_proj.bias": "model-19-of-35.safetensors", | |
| "model.layers.18.self_attn.v_proj.bias": "model-19-of-35.safetensors", | |
| "model.layers.18.input_layernorm.weight": "model-19-of-35.safetensors", | |
| "model.layers.18.post_attention_layernorm.weight": "model-19-of-35.safetensors", | |
| "model.layers.18.mlp.gate_proj.weight": "model-19-of-35.safetensors", | |
| "model.layers.18.mlp.down_proj.weight": "model-19-of-35.safetensors", | |
| "model.layers.18.mlp.up_proj.weight": "model-19-of-35.safetensors", | |
| "model.layers.18.self_attn.rotary_emb.inv_freq": "model-19-of-35.safetensors", | |
| "model.layers.19.self_attn.q_proj.weight": "model-20-of-35.safetensors", | |
| "model.layers.19.self_attn.k_proj.weight": "model-20-of-35.safetensors", | |
| "model.layers.19.self_attn.v_proj.weight": "model-20-of-35.safetensors", | |
| "model.layers.19.self_attn.o_proj.weight": "model-20-of-35.safetensors", | |
| "model.layers.19.self_attn.q_proj.bias": "model-20-of-35.safetensors", | |
| "model.layers.19.self_attn.k_proj.bias": "model-20-of-35.safetensors", | |
| "model.layers.19.self_attn.v_proj.bias": "model-20-of-35.safetensors", | |
| "model.layers.19.input_layernorm.weight": "model-20-of-35.safetensors", | |
| "model.layers.19.post_attention_layernorm.weight": "model-20-of-35.safetensors", | |
| "model.layers.19.mlp.gate_proj.weight": "model-20-of-35.safetensors", | |
| "model.layers.19.mlp.down_proj.weight": "model-20-of-35.safetensors", | |
| "model.layers.19.mlp.up_proj.weight": "model-20-of-35.safetensors", | |
| "model.layers.19.self_attn.rotary_emb.inv_freq": "model-20-of-35.safetensors", | |
| "model.layers.20.self_attn.q_proj.weight": "model-21-of-35.safetensors", | |
| "model.layers.20.self_attn.k_proj.weight": "model-21-of-35.safetensors", | |
| "model.layers.20.self_attn.v_proj.weight": "model-21-of-35.safetensors", | |
| "model.layers.20.self_attn.o_proj.weight": "model-21-of-35.safetensors", | |
| "model.layers.20.self_attn.q_proj.bias": "model-21-of-35.safetensors", | |
| "model.layers.20.self_attn.k_proj.bias": "model-21-of-35.safetensors", | |
| "model.layers.20.self_attn.v_proj.bias": "model-21-of-35.safetensors", | |
| "model.layers.20.input_layernorm.weight": "model-21-of-35.safetensors", | |
| "model.layers.20.post_attention_layernorm.weight": "model-21-of-35.safetensors", | |
| "model.layers.20.mlp.gate_proj.weight": "model-21-of-35.safetensors", | |
| "model.layers.20.mlp.down_proj.weight": "model-21-of-35.safetensors", | |
| "model.layers.20.mlp.up_proj.weight": "model-21-of-35.safetensors", | |
| "model.layers.20.self_attn.rotary_emb.inv_freq": "model-21-of-35.safetensors", | |
| "model.layers.21.self_attn.q_proj.weight": "model-22-of-35.safetensors", | |
| "model.layers.21.self_attn.k_proj.weight": "model-22-of-35.safetensors", | |
| "model.layers.21.self_attn.v_proj.weight": "model-22-of-35.safetensors", | |
| "model.layers.21.self_attn.o_proj.weight": "model-22-of-35.safetensors", | |
| "model.layers.21.self_attn.q_proj.bias": "model-22-of-35.safetensors", | |
| "model.layers.21.self_attn.k_proj.bias": "model-22-of-35.safetensors", | |
| "model.layers.21.self_attn.v_proj.bias": "model-22-of-35.safetensors", | |
| "model.layers.21.input_layernorm.weight": "model-22-of-35.safetensors", | |
| "model.layers.21.post_attention_layernorm.weight": "model-22-of-35.safetensors", | |
| "model.layers.21.mlp.gate_proj.weight": "model-22-of-35.safetensors", | |
| "model.layers.21.mlp.down_proj.weight": "model-22-of-35.safetensors", | |
| "model.layers.21.mlp.up_proj.weight": "model-22-of-35.safetensors", | |
| "model.layers.21.self_attn.rotary_emb.inv_freq": "model-22-of-35.safetensors", | |
| "model.layers.22.self_attn.q_proj.weight": "model-23-of-35.safetensors", | |
| "model.layers.22.self_attn.k_proj.weight": "model-23-of-35.safetensors", | |
| "model.layers.22.self_attn.v_proj.weight": "model-23-of-35.safetensors", | |
| "model.layers.22.self_attn.o_proj.weight": "model-23-of-35.safetensors", | |
| "model.layers.22.self_attn.q_proj.bias": "model-23-of-35.safetensors", | |
| "model.layers.22.self_attn.k_proj.bias": "model-23-of-35.safetensors", | |
| "model.layers.22.self_attn.v_proj.bias": "model-23-of-35.safetensors", | |
| "model.layers.22.input_layernorm.weight": "model-23-of-35.safetensors", | |
| "model.layers.22.post_attention_layernorm.weight": "model-23-of-35.safetensors", | |
| "model.layers.22.mlp.gate_proj.weight": "model-23-of-35.safetensors", | |
| "model.layers.22.mlp.down_proj.weight": "model-23-of-35.safetensors", | |
| "model.layers.22.mlp.up_proj.weight": "model-23-of-35.safetensors", | |
| "model.layers.22.self_attn.rotary_emb.inv_freq": "model-23-of-35.safetensors", | |
| "model.layers.23.self_attn.q_proj.weight": "model-24-of-35.safetensors", | |
| "model.layers.23.self_attn.k_proj.weight": "model-24-of-35.safetensors", | |
| "model.layers.23.self_attn.v_proj.weight": "model-24-of-35.safetensors", | |
| "model.layers.23.self_attn.o_proj.weight": "model-24-of-35.safetensors", | |
| "model.layers.23.self_attn.q_proj.bias": "model-24-of-35.safetensors", | |
| "model.layers.23.self_attn.k_proj.bias": "model-24-of-35.safetensors", | |
| "model.layers.23.self_attn.v_proj.bias": "model-24-of-35.safetensors", | |
| "model.layers.23.input_layernorm.weight": "model-24-of-35.safetensors", | |
| "model.layers.23.post_attention_layernorm.weight": "model-24-of-35.safetensors", | |
| "model.layers.23.mlp.gate_proj.weight": "model-24-of-35.safetensors", | |
| "model.layers.23.mlp.down_proj.weight": "model-24-of-35.safetensors", | |
| "model.layers.23.mlp.up_proj.weight": "model-24-of-35.safetensors", | |
| "model.layers.23.self_attn.rotary_emb.inv_freq": "model-24-of-35.safetensors", | |
| "model.layers.24.self_attn.q_proj.weight": "model-25-of-35.safetensors", | |
| "model.layers.24.self_attn.k_proj.weight": "model-25-of-35.safetensors", | |
| "model.layers.24.self_attn.v_proj.weight": "model-25-of-35.safetensors", | |
| "model.layers.24.self_attn.o_proj.weight": "model-25-of-35.safetensors", | |
| "model.layers.24.self_attn.q_proj.bias": "model-25-of-35.safetensors", | |
| "model.layers.24.self_attn.k_proj.bias": "model-25-of-35.safetensors", | |
| "model.layers.24.self_attn.v_proj.bias": "model-25-of-35.safetensors", | |
| "model.layers.24.input_layernorm.weight": "model-25-of-35.safetensors", | |
| "model.layers.24.post_attention_layernorm.weight": "model-25-of-35.safetensors", | |
| "model.layers.24.mlp.gate_proj.weight": "model-25-of-35.safetensors", | |
| "model.layers.24.mlp.down_proj.weight": "model-25-of-35.safetensors", | |
| "model.layers.24.mlp.up_proj.weight": "model-25-of-35.safetensors", | |
| "model.layers.24.self_attn.rotary_emb.inv_freq": "model-25-of-35.safetensors", | |
| "model.layers.25.self_attn.q_proj.weight": "model-26-of-35.safetensors", | |
| "model.layers.25.self_attn.k_proj.weight": "model-26-of-35.safetensors", | |
| "model.layers.25.self_attn.v_proj.weight": "model-26-of-35.safetensors", | |
| "model.layers.25.self_attn.o_proj.weight": "model-26-of-35.safetensors", | |
| "model.layers.25.self_attn.q_proj.bias": "model-26-of-35.safetensors", | |
| "model.layers.25.self_attn.k_proj.bias": "model-26-of-35.safetensors", | |
| "model.layers.25.self_attn.v_proj.bias": "model-26-of-35.safetensors", | |
| "model.layers.25.input_layernorm.weight": "model-26-of-35.safetensors", | |
| "model.layers.25.post_attention_layernorm.weight": "model-26-of-35.safetensors", | |
| "model.layers.25.mlp.gate_proj.weight": "model-26-of-35.safetensors", | |
| "model.layers.25.mlp.down_proj.weight": "model-26-of-35.safetensors", | |
| "model.layers.25.mlp.up_proj.weight": "model-26-of-35.safetensors", | |
| "model.layers.25.self_attn.rotary_emb.inv_freq": "model-26-of-35.safetensors", | |
| "model.layers.26.self_attn.q_proj.weight": "model-27-of-35.safetensors", | |
| "model.layers.26.self_attn.k_proj.weight": "model-27-of-35.safetensors", | |
| "model.layers.26.self_attn.v_proj.weight": "model-27-of-35.safetensors", | |
| "model.layers.26.self_attn.o_proj.weight": "model-27-of-35.safetensors", | |
| "model.layers.26.self_attn.q_proj.bias": "model-27-of-35.safetensors", | |
| "model.layers.26.self_attn.k_proj.bias": "model-27-of-35.safetensors", | |
| "model.layers.26.self_attn.v_proj.bias": "model-27-of-35.safetensors", | |
| "model.layers.26.input_layernorm.weight": "model-27-of-35.safetensors", | |
| "model.layers.26.post_attention_layernorm.weight": "model-27-of-35.safetensors", | |
| "model.layers.26.mlp.gate_proj.weight": "model-27-of-35.safetensors", | |
| "model.layers.26.mlp.down_proj.weight": "model-27-of-35.safetensors", | |
| "model.layers.26.mlp.up_proj.weight": "model-27-of-35.safetensors", | |
| "model.layers.26.self_attn.rotary_emb.inv_freq": "model-27-of-35.safetensors", | |
| "model.layers.27.self_attn.q_proj.weight": "model-28-of-35.safetensors", | |
| "model.layers.27.self_attn.k_proj.weight": "model-28-of-35.safetensors", | |
| "model.layers.27.self_attn.v_proj.weight": "model-28-of-35.safetensors", | |
| "model.layers.27.self_attn.o_proj.weight": "model-28-of-35.safetensors", | |
| "model.layers.27.self_attn.q_proj.bias": "model-28-of-35.safetensors", | |
| "model.layers.27.self_attn.k_proj.bias": "model-28-of-35.safetensors", | |
| "model.layers.27.self_attn.v_proj.bias": "model-28-of-35.safetensors", | |
| "model.layers.27.input_layernorm.weight": "model-28-of-35.safetensors", | |
| "model.layers.27.post_attention_layernorm.weight": "model-28-of-35.safetensors", | |
| "model.layers.27.mlp.gate_proj.weight": "model-28-of-35.safetensors", | |
| "model.layers.27.mlp.down_proj.weight": "model-28-of-35.safetensors", | |
| "model.layers.27.mlp.up_proj.weight": "model-28-of-35.safetensors", | |
| "model.layers.27.self_attn.rotary_emb.inv_freq": "model-28-of-35.safetensors", | |
| "model.mimo_layers.0.self_attn.q_proj.weight": "model-29-of-35.safetensors", | |
| "model.mimo_layers.0.self_attn.k_proj.weight": "model-29-of-35.safetensors", | |
| "model.mimo_layers.0.self_attn.v_proj.weight": "model-29-of-35.safetensors", | |
| "model.mimo_layers.0.self_attn.o_proj.weight": "model-29-of-35.safetensors", | |
| "model.mimo_layers.0.input_layernorm.weight": "model-29-of-35.safetensors", | |
| "model.mimo_layers.0.post_attention_layernorm.weight": "model-29-of-35.safetensors", | |
| "model.mimo_layers.0.mlp.gate_proj.weight": "model-29-of-35.safetensors", | |
| "model.mimo_layers.0.mlp.down_proj.weight": "model-29-of-35.safetensors", | |
| "model.mimo_layers.0.mlp.up_proj.weight": "model-29-of-35.safetensors", | |
| "model.mimo_layers.0.self_attn.q_proj.bias": "model-29-of-35.safetensors", | |
| "model.mimo_layers.0.self_attn.k_proj.bias": "model-29-of-35.safetensors", | |
| "model.mimo_layers.0.self_attn.v_proj.bias": "model-29-of-35.safetensors", | |
| "model.mimo_layers.0.self_attn.rotary_emb.inv_freq": "model-29-of-35.safetensors", | |
| "model.mimo_layers.1.self_attn.q_proj.weight": "model-30-of-35.safetensors", | |
| "model.mimo_layers.1.self_attn.k_proj.weight": "model-30-of-35.safetensors", | |
| "model.mimo_layers.1.self_attn.v_proj.weight": "model-30-of-35.safetensors", | |
| "model.mimo_layers.1.self_attn.o_proj.weight": "model-30-of-35.safetensors", | |
| "model.mimo_layers.1.input_layernorm.weight": "model-30-of-35.safetensors", | |
| "model.mimo_layers.1.post_attention_layernorm.weight": "model-30-of-35.safetensors", | |
| "model.mimo_layers.1.mlp.gate_proj.weight": "model-30-of-35.safetensors", | |
| "model.mimo_layers.1.mlp.down_proj.weight": "model-30-of-35.safetensors", | |
| "model.mimo_layers.1.mlp.up_proj.weight": "model-30-of-35.safetensors", | |
| "model.mimo_layers.1.self_attn.q_proj.bias": "model-30-of-35.safetensors", | |
| "model.mimo_layers.1.self_attn.k_proj.bias": "model-30-of-35.safetensors", | |
| "model.mimo_layers.1.self_attn.v_proj.bias": "model-30-of-35.safetensors", | |
| "model.mimo_layers.1.self_attn.rotary_emb.inv_freq": "model-30-of-35.safetensors", | |
| "model.mimo_layers.2.self_attn.q_proj.weight": "model-31-of-35.safetensors", | |
| "model.mimo_layers.2.self_attn.k_proj.weight": "model-31-of-35.safetensors", | |
| "model.mimo_layers.2.self_attn.v_proj.weight": "model-31-of-35.safetensors", | |
| "model.mimo_layers.2.self_attn.o_proj.weight": "model-31-of-35.safetensors", | |
| "model.mimo_layers.2.input_layernorm.weight": "model-31-of-35.safetensors", | |
| "model.mimo_layers.2.post_attention_layernorm.weight": "model-31-of-35.safetensors", | |
| "model.mimo_layers.2.mlp.gate_proj.weight": "model-31-of-35.safetensors", | |
| "model.mimo_layers.2.mlp.down_proj.weight": "model-31-of-35.safetensors", | |
| "model.mimo_layers.2.mlp.up_proj.weight": "model-31-of-35.safetensors", | |
| "model.mimo_layers.2.self_attn.q_proj.bias": "model-31-of-35.safetensors", | |
| "model.mimo_layers.2.self_attn.k_proj.bias": "model-31-of-35.safetensors", | |
| "model.mimo_layers.2.self_attn.v_proj.bias": "model-31-of-35.safetensors", | |
| "model.mimo_layers.2.self_attn.rotary_emb.inv_freq": "model-31-of-35.safetensors", | |
| "model.mimo_layers.3.self_attn.q_proj.weight": "model-32-of-35.safetensors", | |
| "model.mimo_layers.3.self_attn.k_proj.weight": "model-32-of-35.safetensors", | |
| "model.mimo_layers.3.self_attn.v_proj.weight": "model-32-of-35.safetensors", | |
| "model.mimo_layers.3.self_attn.o_proj.weight": "model-32-of-35.safetensors", | |
| "model.mimo_layers.3.input_layernorm.weight": "model-32-of-35.safetensors", | |
| "model.mimo_layers.3.post_attention_layernorm.weight": "model-32-of-35.safetensors", | |
| "model.mimo_layers.3.mlp.gate_proj.weight": "model-32-of-35.safetensors", | |
| "model.mimo_layers.3.mlp.down_proj.weight": "model-32-of-35.safetensors", | |
| "model.mimo_layers.3.mlp.up_proj.weight": "model-32-of-35.safetensors", | |
| "model.mimo_layers.3.self_attn.q_proj.bias": "model-32-of-35.safetensors", | |
| "model.mimo_layers.3.self_attn.k_proj.bias": "model-32-of-35.safetensors", | |
| "model.mimo_layers.3.self_attn.v_proj.bias": "model-32-of-35.safetensors", | |
| "model.mimo_layers.3.self_attn.rotary_emb.inv_freq": "model-32-of-35.safetensors", | |
| "model.mimo_layers.4.self_attn.q_proj.weight": "model-33-of-35.safetensors", | |
| "model.mimo_layers.4.self_attn.k_proj.weight": "model-33-of-35.safetensors", | |
| "model.mimo_layers.4.self_attn.v_proj.weight": "model-33-of-35.safetensors", | |
| "model.mimo_layers.4.self_attn.o_proj.weight": "model-33-of-35.safetensors", | |
| "model.mimo_layers.4.input_layernorm.weight": "model-33-of-35.safetensors", | |
| "model.mimo_layers.4.post_attention_layernorm.weight": "model-33-of-35.safetensors", | |
| "model.mimo_layers.4.mlp.gate_proj.weight": "model-33-of-35.safetensors", | |
| "model.mimo_layers.4.mlp.down_proj.weight": "model-33-of-35.safetensors", | |
| "model.mimo_layers.4.mlp.up_proj.weight": "model-33-of-35.safetensors", | |
| "model.mimo_layers.4.self_attn.q_proj.bias": "model-33-of-35.safetensors", | |
| "model.mimo_layers.4.self_attn.k_proj.bias": "model-33-of-35.safetensors", | |
| "model.mimo_layers.4.self_attn.v_proj.bias": "model-33-of-35.safetensors", | |
| "model.mimo_layers.4.self_attn.rotary_emb.inv_freq": "model-33-of-35.safetensors", | |
| "model.mimo_layers.5.self_attn.q_proj.weight": "model-34-of-35.safetensors", | |
| "model.mimo_layers.5.self_attn.k_proj.weight": "model-34-of-35.safetensors", | |
| "model.mimo_layers.5.self_attn.v_proj.weight": "model-34-of-35.safetensors", | |
| "model.mimo_layers.5.self_attn.o_proj.weight": "model-34-of-35.safetensors", | |
| "model.mimo_layers.5.input_layernorm.weight": "model-34-of-35.safetensors", | |
| "model.mimo_layers.5.post_attention_layernorm.weight": "model-34-of-35.safetensors", | |
| "model.mimo_layers.5.mlp.gate_proj.weight": "model-34-of-35.safetensors", | |
| "model.mimo_layers.5.mlp.down_proj.weight": "model-34-of-35.safetensors", | |
| "model.mimo_layers.5.mlp.up_proj.weight": "model-34-of-35.safetensors", | |
| "model.mimo_layers.5.self_attn.q_proj.bias": "model-34-of-35.safetensors", | |
| "model.mimo_layers.5.self_attn.k_proj.bias": "model-34-of-35.safetensors", | |
| "model.mimo_layers.5.self_attn.v_proj.bias": "model-34-of-35.safetensors", | |
| "model.mimo_layers.5.self_attn.rotary_emb.inv_freq": "model-34-of-35.safetensors", | |
| "model.vq_adaptor.layers.0.weight": "model-35-of-35.safetensors", | |
| "model.vq_adaptor.layers.0.bias": "model-35-of-35.safetensors", | |
| "model.vq_adaptor.layers.3.weight": "model-35-of-35.safetensors", | |
| "model.vq_adaptor.layers.3.bias": "model-35-of-35.safetensors", | |
| "model.vq_adaptor.layers.4.weight": "model-35-of-35.safetensors", | |
| "model.vq_adaptor.layers.4.bias": "model-35-of-35.safetensors", | |
| "model.embed_tokens.weight": "model-36-of-36.safetensors", | |
| "model.norm.weight": "model-36-of-36.safetensors", | |
| "lm_head.weight": "model-36-of-36.safetensors", | |
| "mimo_output.weight": "model-36-of-36.safetensors", | |
| "model.mimo_norm.weight": "model-36-of-36.safetensors" | |
| } | |
| } |