| { | |
| "metadata": { | |
| "total_size": 22412795904 | |
| }, | |
| "weight_map": { | |
| "lm_head.weight": "model-00001-of-00005.safetensors", | |
| "model.embed_tokens.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.0.experts.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.0.experts.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.0.experts.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.0.experts.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.0.experts.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.0.experts.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.0.lora.lora_A": "model-00001-of-00005.safetensors", | |
| "model.layers.0.lora.lora_B": "model-00001-of-00005.safetensors", | |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.1.experts.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.1.experts.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.1.experts.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.1.experts.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.1.experts.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.1.experts.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.1.lora.lora_A": "model-00001-of-00005.safetensors", | |
| "model.layers.1.lora.lora_B": "model-00001-of-00005.safetensors", | |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.10.experts.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.10.experts.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.10.experts.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.10.experts.1.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.10.experts.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.10.experts.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.10.lora.lora_A": "model-00002-of-00005.safetensors", | |
| "model.layers.10.lora.lora_B": "model-00002-of-00005.safetensors", | |
| "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.11.experts.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.11.experts.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.11.experts.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.11.experts.1.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.11.experts.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.11.experts.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.11.lora.lora_A": "model-00002-of-00005.safetensors", | |
| "model.layers.11.lora.lora_B": "model-00002-of-00005.safetensors", | |
| "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.12.experts.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.12.experts.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.12.experts.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.12.experts.1.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.12.experts.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.12.experts.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.12.lora.lora_A": "model-00002-of-00005.safetensors", | |
| "model.layers.12.lora.lora_B": "model-00002-of-00005.safetensors", | |
| "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.13.experts.0.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.13.experts.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.13.experts.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.13.experts.1.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.13.experts.1.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.13.experts.1.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.13.lora.lora_A": "model-00003-of-00005.safetensors", | |
| "model.layers.13.lora.lora_B": "model-00003-of-00005.safetensors", | |
| "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.14.experts.0.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.14.experts.0.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.14.experts.0.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.14.experts.1.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.14.experts.1.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.14.experts.1.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.14.lora.lora_A": "model-00003-of-00005.safetensors", | |
| "model.layers.14.lora.lora_B": "model-00003-of-00005.safetensors", | |
| "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.15.experts.0.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.15.experts.0.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.15.experts.0.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.15.experts.1.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.15.experts.1.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.15.experts.1.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.15.lora.lora_A": "model-00003-of-00005.safetensors", | |
| "model.layers.15.lora.lora_B": "model-00003-of-00005.safetensors", | |
| "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.16.experts.0.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.16.experts.0.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.16.experts.0.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.16.experts.1.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.16.experts.1.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.16.experts.1.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.16.lora.lora_A": "model-00003-of-00005.safetensors", | |
| "model.layers.16.lora.lora_B": "model-00003-of-00005.safetensors", | |
| "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.17.experts.0.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.17.experts.0.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.17.experts.0.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.17.experts.1.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.17.experts.1.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.17.experts.1.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.17.lora.lora_A": "model-00003-of-00005.safetensors", | |
| "model.layers.17.lora.lora_B": "model-00003-of-00005.safetensors", | |
| "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.18.experts.0.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.18.experts.0.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.18.experts.0.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.18.experts.1.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.18.experts.1.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.18.experts.1.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.18.lora.lora_A": "model-00003-of-00005.safetensors", | |
| "model.layers.18.lora.lora_B": "model-00003-of-00005.safetensors", | |
| "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.19.experts.0.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.19.experts.0.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.19.experts.0.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.19.experts.1.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.19.experts.1.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.19.experts.1.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.19.lora.lora_A": "model-00003-of-00005.safetensors", | |
| "model.layers.19.lora.lora_B": "model-00003-of-00005.safetensors", | |
| "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.2.experts.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.2.experts.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.2.experts.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.2.experts.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.2.experts.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.2.experts.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.2.lora.lora_A": "model-00001-of-00005.safetensors", | |
| "model.layers.2.lora.lora_B": "model-00001-of-00005.safetensors", | |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.20.experts.0.mlp.down_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.20.experts.0.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.20.experts.0.mlp.up_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.20.experts.1.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.20.experts.1.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.20.experts.1.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.20.lora.lora_A": "model-00004-of-00005.safetensors", | |
| "model.layers.20.lora.lora_B": "model-00004-of-00005.safetensors", | |
| "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", | |
| "model.layers.21.experts.0.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.21.experts.0.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.21.experts.0.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.21.experts.1.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.21.experts.1.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.21.experts.1.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.21.lora.lora_A": "model-00004-of-00005.safetensors", | |
| "model.layers.21.lora.lora_B": "model-00004-of-00005.safetensors", | |
| "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.22.experts.0.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.22.experts.0.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.22.experts.0.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.22.experts.1.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.22.experts.1.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.22.experts.1.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.22.lora.lora_A": "model-00004-of-00005.safetensors", | |
| "model.layers.22.lora.lora_B": "model-00004-of-00005.safetensors", | |
| "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.23.experts.0.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.23.experts.0.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.23.experts.0.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.23.experts.1.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.23.experts.1.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.23.experts.1.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.23.lora.lora_A": "model-00004-of-00005.safetensors", | |
| "model.layers.23.lora.lora_B": "model-00004-of-00005.safetensors", | |
| "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.24.experts.0.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.24.experts.0.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.24.experts.0.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.24.experts.1.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.24.experts.1.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.24.experts.1.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.24.lora.lora_A": "model-00004-of-00005.safetensors", | |
| "model.layers.24.lora.lora_B": "model-00004-of-00005.safetensors", | |
| "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.25.experts.0.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.25.experts.0.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.25.experts.0.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.25.experts.1.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.25.experts.1.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.25.experts.1.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.25.lora.lora_A": "model-00004-of-00005.safetensors", | |
| "model.layers.25.lora.lora_B": "model-00004-of-00005.safetensors", | |
| "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.26.experts.0.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.26.experts.0.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.26.experts.0.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.26.experts.1.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.26.experts.1.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.26.experts.1.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.26.lora.lora_A": "model-00004-of-00005.safetensors", | |
| "model.layers.26.lora.lora_B": "model-00004-of-00005.safetensors", | |
| "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.27.experts.0.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.27.experts.0.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.27.experts.0.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.27.experts.1.mlp.down_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.27.experts.1.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.27.experts.1.mlp.up_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.27.lora.lora_A": "model-00004-of-00005.safetensors", | |
| "model.layers.27.lora.lora_B": "model-00004-of-00005.safetensors", | |
| "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.28.experts.0.mlp.down_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.28.experts.0.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.28.experts.0.mlp.up_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.28.experts.1.mlp.down_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.28.experts.1.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.28.experts.1.mlp.up_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.28.lora.lora_A": "model-00005-of-00005.safetensors", | |
| "model.layers.28.lora.lora_B": "model-00005-of-00005.safetensors", | |
| "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", | |
| "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.29.experts.0.mlp.down_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.29.experts.0.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.29.experts.0.mlp.up_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.29.experts.1.mlp.down_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.29.experts.1.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.29.experts.1.mlp.up_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.29.input_layernorm.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.29.lora.lora_A": "model-00005-of-00005.safetensors", | |
| "model.layers.29.lora.lora_B": "model-00005-of-00005.safetensors", | |
| "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.3.experts.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.3.experts.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.3.experts.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.3.experts.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.3.experts.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.3.experts.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.3.lora.lora_A": "model-00001-of-00005.safetensors", | |
| "model.layers.3.lora.lora_B": "model-00001-of-00005.safetensors", | |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.30.experts.0.mlp.down_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.30.experts.0.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.30.experts.0.mlp.up_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.30.experts.1.mlp.down_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.30.experts.1.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.30.experts.1.mlp.up_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.30.input_layernorm.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.30.lora.lora_A": "model-00005-of-00005.safetensors", | |
| "model.layers.30.lora.lora_B": "model-00005-of-00005.safetensors", | |
| "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.31.experts.0.mlp.down_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.31.experts.0.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.31.experts.0.mlp.up_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.31.experts.1.mlp.down_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.31.experts.1.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.31.experts.1.mlp.up_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.31.input_layernorm.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.31.lora.lora_A": "model-00005-of-00005.safetensors", | |
| "model.layers.31.lora.lora_B": "model-00005-of-00005.safetensors", | |
| "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", | |
| "model.layers.4.experts.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.4.experts.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.4.experts.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.4.experts.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.4.experts.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.4.experts.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.4.lora.lora_A": "model-00001-of-00005.safetensors", | |
| "model.layers.4.lora.lora_B": "model-00001-of-00005.safetensors", | |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.5.experts.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.5.experts.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.5.experts.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.5.experts.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.5.experts.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.5.experts.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.5.lora.lora_A": "model-00001-of-00005.safetensors", | |
| "model.layers.5.lora.lora_B": "model-00001-of-00005.safetensors", | |
| "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.6.experts.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.6.experts.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.6.experts.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.6.experts.1.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.6.experts.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.6.experts.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.6.lora.lora_A": "model-00002-of-00005.safetensors", | |
| "model.layers.6.lora.lora_B": "model-00002-of-00005.safetensors", | |
| "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", | |
| "model.layers.7.experts.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.7.experts.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.7.experts.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.7.experts.1.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.7.experts.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.7.experts.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.7.lora.lora_A": "model-00002-of-00005.safetensors", | |
| "model.layers.7.lora.lora_B": "model-00002-of-00005.safetensors", | |
| "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.8.experts.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.8.experts.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.8.experts.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.8.experts.1.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.8.experts.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.8.experts.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.8.lora.lora_A": "model-00002-of-00005.safetensors", | |
| "model.layers.8.lora.lora_B": "model-00002-of-00005.safetensors", | |
| "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.9.experts.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.9.experts.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.9.experts.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.9.experts.1.mlp.down_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.9.experts.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.9.experts.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.9.lora.lora_A": "model-00002-of-00005.safetensors", | |
| "model.layers.9.lora.lora_B": "model-00002-of-00005.safetensors", | |
| "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", | |
| "model.norm.weight": "model-00005-of-00005.safetensors" | |
| } | |
| } | |