Missing key(s) in state_dict

[lgs00]

Thanks for sharing the code, when I was running the demo, I downloaded the pre-trained model, but reported an error.

RuntimeError: Error(s) in loading state_dict for MiniGPT4:
        Missing key(s) in state_dict: "llama_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight"

[jaepoong]

Please shows the entire error?
i can't specify the exact error point.

[Zhenjiang-Liu]

I met the problem too.

when I use CodeLlama-7b-hf and processed_code's ptorch_model.bin, the entire error is:

RuntimeError Traceback (most recent call last)
Cell In[2], line 16
14 base_model = "processed_code/model_weight/train_stage1_dino_code_llama/pytorch_model.bin"
15 model = MiniGPT4(lora_r=64,low_resource=False,vit_model = vit_model_name,llama_model = llama_model)
---> 16 model.load_state_dict(torch.load(base_model,map_location="cpu"))
17 model = model.to(device)
18 model.device = device

File /mnt/workspace/workgroup/pinyuan/ENV/posterlmama/lib/python3.9/site-packages/torch/nn/modules/module.py:2581, in Module.load_state_dict(self, state_dict, strict, assign)
2573 error_msgs.insert(
2574 0,
2575 "Missing key(s) in state_dict: {}. ".format(
2576 ", ".join(f'"{k}"' for k in missing_keys)
2577 ),
2578 )
2580 if len(error_msgs) > 0:
-> 2581 raise RuntimeError(
2582 "Error(s) in loading state_dict for {}:\n\t{}".format(
2583 self.class.name, "\n\t".join(error_msgs)
2584 )
2585 )
2586 return _IncompatibleKeys(missing_keys, unexpected_keys)

RuntimeError: Error(s) in loading state_dict for MiniGPT4:
Missing key(s) in state_dict: "llama_model.base_model.model.model.embed_tokens.weight", "llama_model.base_model.model.model.layers.0.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.0.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.0.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.0.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.0.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.0.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.0.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.0.input_layernorm.weight", "llama_model.base_model.model.model.layers.0.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.1.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.1.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.1.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.1.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.1.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.1.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.1.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.1.input_layernorm.weight", "llama_model.base_model.model.model.layers.1.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.2.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.2.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.2.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.2.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.2.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.2.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.2.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.2.input_layernorm.weight", "llama_model.base_model.model.model.layers.2.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.3.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.3.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.3.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.3.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.3.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.3.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.3.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.3.input_layernorm.weight", "llama_model.base_model.model.model.layers.3.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.4.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.4.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.4.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.4.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.4.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.4.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.4.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.4.input_layernorm.weight", "llama_model.base_model.model.model.layers.4.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.5.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.5.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.5.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.5.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.5.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.5.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.5.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.5.input_layernorm.weight", "llama_model.base_model.model.model.layers.5.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.6.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.6.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.6.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.6.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.6.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.6.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.6.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.6.input_layernorm.weight", "llama_model.base_model.model.model.layers.6.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.7.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.7.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.7.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.7.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.7.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.7.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.7.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.7.input_layernorm.weight", "llama_model.base_model.model.model.layers.7.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.8.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.8.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.8.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.8.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.8.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.8.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.8.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.8.input_layernorm.weight", "llama_model.base_model.model.model.layers.8.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.9.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.9.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.9.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.9.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.9.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.9.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.9.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.9.input_layernorm.weight", "llama_model.base_model.model.model.layers.9.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.10.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.10.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.10.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.10.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.10.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.10.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.10.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.10.input_layernorm.weight", "llama_model.base_model.model.model.layers.10.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.11.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.11.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.11.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.11.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.11.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.11.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.11.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.11.input_layernorm.weight", "llama_model.base_model.model.model.layers.11.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.12.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.12.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.12.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.12.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.12.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.12.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.12.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.12.input_layernorm.weight", "llama_model.base_model.model.model.layers.12.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.13.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.13.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.13.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.13.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.13.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.13.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.13.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.13.input_layernorm.weight", "llama_model.base_model.model.model.layers.13.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.14.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.14.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.14.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.14.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.14.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.14.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.14.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.14.input_layernorm.weight", "llama_model.base_model.model.model.layers.14.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.15.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.15.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.15.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.15.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.15.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.15.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.15.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.15.input_layernorm.weight", "llama_model.base_model.model.model.layers.15.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.16.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.16.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.16.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.16.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.16.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.16.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.16.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.16.input_layernorm.weight", "llama_model.base_model.model.model.layers.16.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.17.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.17.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.17.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.17.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.17.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.17.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.17.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.17.input_layernorm.weight", "llama_model.base_model.model.model.layers.17.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.18.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.18.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.18.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.18.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.18.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.18.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.18.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.18.input_layernorm.weight", "llama_model.base_model.model.model.layers.18.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.19.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.19.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.19.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.19.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.19.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.19.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.19.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.19.input_layernorm.weight", "llama_model.base_model.model.model.layers.19.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.20.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.20.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.20.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.20.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.20.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.20.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.20.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.20.input_layernorm.weight", "llama_model.base_model.model.model.layers.20.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.21.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.21.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.21.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.21.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.21.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.21.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.21.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.21.input_layernorm.weight", "llama_model.base_model.model.model.layers.21.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.22.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.22.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.22.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.22.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.22.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.22.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.22.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.22.input_layernorm.weight", "llama_model.base_model.model.model.layers.22.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.23.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.23.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.23.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.23.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.23.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.23.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.23.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.23.input_layernorm.weight", "llama_model.base_model.model.model.layers.23.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.24.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.24.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.24.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.24.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.24.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.24.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.24.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.24.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.24.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.24.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.24.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.24.input_layernorm.weight", "llama_model.base_model.model.model.layers.24.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.25.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.25.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.25.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.25.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.25.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.25.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.25.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.25.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.25.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.25.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.25.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.25.input_layernorm.weight", "llama_model.base_model.model.model.layers.25.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.26.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.26.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.26.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.26.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.26.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.26.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.26.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.26.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.26.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.26.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.26.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.26.input_layernorm.weight", "llama_model.base_model.model.model.layers.26.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.27.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.27.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.27.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.27.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.27.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.27.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.27.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.27.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.27.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.27.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.27.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.27.input_layernorm.weight", "llama_model.base_model.model.model.layers.27.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.28.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.28.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.28.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.28.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.28.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.28.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.28.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.28.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.28.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.28.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.28.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.28.input_layernorm.weight", "llama_model.base_model.model.model.layers.28.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.29.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.29.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.29.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.29.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.29.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.29.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.29.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.29.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.29.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.29.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.29.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.29.input_layernorm.weight", "llama_model.base_model.model.model.layers.29.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.30.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.30.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.30.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.30.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.30.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.30.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.30.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.30.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.30.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.30.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.30.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.30.input_layernorm.weight", "llama_model.base_model.model.model.layers.30.post_attention_layernorm.weight", "llama_model.base_model.model.model.layers.31.self_attn.q_proj.weight", "llama_model.base_model.model.model.layers.31.self_attn.q_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.31.self_attn.q_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.31.self_attn.k_proj.weight", "llama_model.base_model.model.model.layers.31.self_attn.v_proj.weight", "llama_model.base_model.model.model.layers.31.self_attn.v_proj.lora_A.default.weight", "llama_model.base_model.model.model.layers.31.self_attn.v_proj.lora_B.default.weight", "llama_model.base_model.model.model.layers.31.self_attn.o_proj.weight", "llama_model.base_model.model.model.layers.31.mlp.gate_proj.weight", "llama_model.base_model.model.model.layers.31.mlp.up_proj.weight", "llama_model.base_model.model.model.layers.31.mlp.down_proj.weight", "llama_model.base_model.model.model.layers.31.input_layernorm.weight", "llama_model.base_model.model.model.layers.31.post_attention_layernorm.weight", "llama_model.base_model.model.model.norm.weight", "llama_model.base_model.model.lm_head.weight".
Unexpected key(s) in state_dict: "llama_model.model.embed_tokens.weight", "llama_model.model.layers.0.self_attn.q_proj.weight", "llama_model.model.layers.0.self_attn.k_proj.weight", "llama_model.model.layers.0.self_attn.v_proj.weight", "llama_model.model.layers.0.self_attn.o_proj.weight", "llama_model.model.layers.0.mlp.gate_proj.weight", "llama_model.model.layers.0.mlp.up_proj.weight", "llama_model.model.layers.0.mlp.down_proj.weight", "llama_model.model.layers.0.input_layernorm.weight", "llama_model.model.layers.0.post_attention_layernorm.weight", "llama_model.model.layers.1.self_attn.q_proj.weight", "llama_model.model.layers.1.self_attn.k_proj.weight", "llama_model.model.layers.1.self_attn.v_proj.weight", "llama_model.model.layers.1.self_attn.o_proj.weight", "llama_model.model.layers.1.mlp.gate_proj.weight", "llama_model.model.layers.1.mlp.up_proj.weight", "llama_model.model.layers.1.mlp.down_proj.weight", "llama_model.model.layers.1.input_layernorm.weight", "llama_model.model.layers.1.post_attention_layernorm.weight", "llama_model.model.layers.2.self_attn.q_proj.weight", "llama_model.model.layers.2.self_attn.k_proj.weight", "llama_model.model.layers.2.self_attn.v_proj.weight", "llama_model.model.layers.2.self_attn.o_proj.weight", "llama_model.model.layers.2.mlp.gate_proj.weight", "llama_model.model.layers.2.mlp.up_proj.weight", "llama_model.model.layers.2.mlp.down_proj.weight", "llama_model.model.layers.2.input_layernorm.weight", "llama_model.model.layers.2.post_attention_layernorm.weight", "llama_model.model.layers.3.self_attn.q_proj.weight", "llama_model.model.layers.3.self_attn.k_proj.weight", "llama_model.model.layers.3.self_attn.v_proj.weight", "llama_model.model.layers.3.self_attn.o_proj.weight", "llama_model.model.layers.3.mlp.gate_proj.weight", "llama_model.model.layers.3.mlp.up_proj.weight", "llama_model.model.layers.3.mlp.down_proj.weight", "llama_model.model.layers.3.input_layernorm.weight", "llama_model.model.layers.3.post_attention_layernorm.weight", "llama_model.model.layers.4.self_attn.q_proj.weight", "llama_model.model.layers.4.self_attn.k_proj.weight", "llama_model.model.layers.4.self_attn.v_proj.weight", "llama_model.model.layers.4.self_attn.o_proj.weight", "llama_model.model.layers.4.mlp.gate_proj.weight", "llama_model.model.layers.4.mlp.up_proj.weight", "llama_model.model.layers.4.mlp.down_proj.weight", "llama_model.model.layers.4.input_layernorm.weight", "llama_model.model.layers.4.post_attention_layernorm.weight", "llama_model.model.layers.5.self_attn.q_proj.weight", "llama_model.model.layers.5.self_attn.k_proj.weight", "llama_model.model.layers.5.self_attn.v_proj.weight", "llama_model.model.layers.5.self_attn.o_proj.weight", "llama_model.model.layers.5.mlp.gate_proj.weight", "llama_model.model.layers.5.mlp.up_proj.weight", "llama_model.model.layers.5.mlp.down_proj.weight", "llama_model.model.layers.5.input_layernorm.weight", "llama_model.model.layers.5.post_attention_layernorm.weight", "llama_model.model.layers.6.self_attn.q_proj.weight", "llama_model.model.layers.6.self_attn.k_proj.weight", "llama_model.model.layers.6.self_attn.v_proj.weight", "llama_model.model.layers.6.self_attn.o_proj.weight", "llama_model.model.layers.6.mlp.gate_proj.weight", "llama_model.model.layers.6.mlp.up_proj.weight", "llama_model.model.layers.6.mlp.down_proj.weight", "llama_model.model.layers.6.input_layernorm.weight", "llama_model.model.layers.6.post_attention_layernorm.weight", "llama_model.model.layers.7.self_attn.q_proj.weight", "llama_model.model.layers.7.self_attn.k_proj.weight", "llama_model.model.layers.7.self_attn.v_proj.weight", "llama_model.model.layers.7.self_attn.o_proj.weight", "llama_model.model.layers.7.mlp.gate_proj.weight", "llama_model.model.layers.7.mlp.up_proj.weight", "llama_model.model.layers.7.mlp.down_proj.weight", "llama_model.model.layers.7.input_layernorm.weight", "llama_model.model.layers.7.post_attention_layernorm.weight", "llama_model.model.layers.8.self_attn.q_proj.weight", "llama_model.model.layers.8.self_attn.k_proj.weight", "llama_model.model.layers.8.self_attn.v_proj.weight", "llama_model.model.layers.8.self_attn.o_proj.weight", "llama_model.model.layers.8.mlp.gate_proj.weight", "llama_model.model.layers.8.mlp.up_proj.weight", "llama_model.model.layers.8.mlp.down_proj.weight", "llama_model.model.layers.8.input_layernorm.weight", "llama_model.model.layers.8.post_attention_layernorm.weight", "llama_model.model.layers.9.self_attn.q_proj.weight", "llama_model.model.layers.9.self_attn.k_proj.weight", "llama_model.model.layers.9.self_attn.v_proj.weight", "llama_model.model.layers.9.self_attn.o_proj.weight", "llama_model.model.layers.9.mlp.gate_proj.weight", "llama_model.model.layers.9.mlp.up_proj.weight", "llama_model.model.layers.9.mlp.down_proj.weight", "llama_model.model.layers.9.input_layernorm.weight", "llama_model.model.layers.9.post_attention_layernorm.weight", "llama_model.model.layers.10.self_attn.q_proj.weight", "llama_model.model.layers.10.self_attn.k_proj.weight", "llama_model.model.layers.10.self_attn.v_proj.weight", "llama_model.model.layers.10.self_attn.o_proj.weight", "llama_model.model.layers.10.mlp.gate_proj.weight", "llama_model.model.layers.10.mlp.up_proj.weight", "llama_model.model.layers.10.mlp.down_proj.weight", "llama_model.model.layers.10.input_layernorm.weight", "llama_model.model.layers.10.post_attention_layernorm.weight", "llama_model.model.layers.11.self_attn.q_proj.weight", "llama_model.model.layers.11.self_attn.k_proj.weight", "llama_model.model.layers.11.self_attn.v_proj.weight", "llama_model.model.layers.11.self_attn.o_proj.weight", "llama_model.model.layers.11.mlp.gate_proj.weight", "llama_model.model.layers.11.mlp.up_proj.weight", "llama_model.model.layers.11.mlp.down_proj.weight", "llama_model.model.layers.11.input_layernorm.weight", "llama_model.model.layers.11.post_attention_layernorm.weight", "llama_model.model.layers.12.self_attn.q_proj.weight", "llama_model.model.layers.12.self_attn.k_proj.weight", "llama_model.model.layers.12.self_attn.v_proj.weight", "llama_model.model.layers.12.self_attn.o_proj.weight", "llama_model.model.layers.12.mlp.gate_proj.weight", "llama_model.model.layers.12.mlp.up_proj.weight", "llama_model.model.layers.12.mlp.down_proj.weight", "llama_model.model.layers.12.input_layernorm.weight", "llama_model.model.layers.12.post_attention_layernorm.weight", "llama_model.model.layers.13.self_attn.q_proj.weight", "llama_model.model.layers.13.self_attn.k_proj.weight", "llama_model.model.layers.13.self_attn.v_proj.weight", "llama_model.model.layers.13.self_attn.o_proj.weight", "llama_model.model.layers.13.mlp.gate_proj.weight", "llama_model.model.layers.13.mlp.up_proj.weight", "llama_model.model.layers.13.mlp.down_proj.weight", "llama_model.model.layers.13.input_layernorm.weight", "llama_model.model.layers.13.post_attention_layernorm.weight", "llama_model.model.layers.14.self_attn.q_proj.weight", "llama_model.model.layers.14.self_attn.k_proj.weight", "llama_model.model.layers.14.self_attn.v_proj.weight", "llama_model.model.layers.14.self_attn.o_proj.weight", "llama_model.model.layers.14.mlp.gate_proj.weight", "llama_model.model.layers.14.mlp.up_proj.weight", "llama_model.model.layers.14.mlp.down_proj.weight", "llama_model.model.layers.14.input_layernorm.weight", "llama_model.model.layers.14.post_attention_layernorm.weight", "llama_model.model.layers.15.self_attn.q_proj.weight", "llama_model.model.layers.15.self_attn.k_proj.weight", "llama_model.model.layers.15.self_attn.v_proj.weight", "llama_model.model.layers.15.self_attn.o_proj.weight", "llama_model.model.layers.15.mlp.gate_proj.weight", "llama_model.model.layers.15.mlp.up_proj.weight", "llama_model.model.layers.15.mlp.down_proj.weight", "llama_model.model.layers.15.input_layernorm.weight", "llama_model.model.layers.15.post_attention_layernorm.weight", "llama_model.model.layers.16.self_attn.q_proj.weight", "llama_model.model.layers.16.self_attn.k_proj.weight", "llama_model.model.layers.16.self_attn.v_proj.weight", "llama_model.model.layers.16.self_attn.o_proj.weight", "llama_model.model.layers.16.mlp.gate_proj.weight", "llama_model.model.layers.16.mlp.up_proj.weight", "llama_model.model.layers.16.mlp.down_proj.weight", "llama_model.model.layers.16.input_layernorm.weight", "llama_model.model.layers.16.post_attention_layernorm.weight", "llama_model.model.layers.17.self_attn.q_proj.weight", "llama_model.model.layers.17.self_attn.k_proj.weight", "llama_model.model.layers.17.self_attn.v_proj.weight", "llama_model.model.layers.17.self_attn.o_proj.weight", "llama_model.model.layers.17.mlp.gate_proj.weight", "llama_model.model.layers.17.mlp.up_proj.weight", "llama_model.model.layers.17.mlp.down_proj.weight", "llama_model.model.layers.17.input_layernorm.weight", "llama_model.model.layers.17.post_attention_layernorm.weight", "llama_model.model.layers.18.self_attn.q_proj.weight", "llama_model.model.layers.18.self_attn.k_proj.weight", "llama_model.model.layers.18.self_attn.v_proj.weight", "llama_model.model.layers.18.self_attn.o_proj.weight", "llama_model.model.layers.18.mlp.gate_proj.weight", "llama_model.model.layers.18.mlp.up_proj.weight", "llama_model.model.layers.18.mlp.down_proj.weight", "llama_model.model.layers.18.input_layernorm.weight", "llama_model.model.layers.18.post_attention_layernorm.weight", "llama_model.model.layers.19.self_attn.q_proj.weight", "llama_model.model.layers.19.self_attn.k_proj.weight", "llama_model.model.layers.19.self_attn.v_proj.weight", "llama_model.model.layers.19.self_attn.o_proj.weight", "llama_model.model.layers.19.mlp.gate_proj.weight", "llama_model.model.layers.19.mlp.up_proj.weight", "llama_model.model.layers.19.mlp.down_proj.weight", "llama_model.model.layers.19.input_layernorm.weight", "llama_model.model.layers.19.post_attention_layernorm.weight", "llama_model.model.layers.20.self_attn.q_proj.weight", "llama_model.model.layers.20.self_attn.k_proj.weight", "llama_model.model.layers.20.self_attn.v_proj.weight", "llama_model.model.layers.20.self_attn.o_proj.weight", "llama_model.model.layers.20.mlp.gate_proj.weight", "llama_model.model.layers.20.mlp.up_proj.weight", "llama_model.model.layers.20.mlp.down_proj.weight", "llama_model.model.layers.20.input_layernorm.weight", "llama_model.model.layers.20.post_attention_layernorm.weight", "llama_model.model.layers.21.self_attn.q_proj.weight", "llama_model.model.layers.21.self_attn.k_proj.weight", "llama_model.model.layers.21.self_attn.v_proj.weight", "llama_model.model.layers.21.self_attn.o_proj.weight", "llama_model.model.layers.21.mlp.gate_proj.weight", "llama_model.model.layers.21.mlp.up_proj.weight", "llama_model.model.layers.21.mlp.down_proj.weight", "llama_model.model.layers.21.input_layernorm.weight", "llama_model.model.layers.21.post_attention_layernorm.weight", "llama_model.model.layers.22.self_attn.q_proj.weight", "llama_model.model.layers.22.self_attn.k_proj.weight", "llama_model.model.layers.22.self_attn.v_proj.weight", "llama_model.model.layers.22.self_attn.o_proj.weight", "llama_model.model.layers.22.mlp.gate_proj.weight", "llama_model.model.layers.22.mlp.up_proj.weight", "llama_model.model.layers.22.mlp.down_proj.weight", "llama_model.model.layers.22.input_layernorm.weight", "llama_model.model.layers.22.post_attention_layernorm.weight", "llama_model.model.layers.23.self_attn.q_proj.weight", "llama_model.model.layers.23.self_attn.k_proj.weight", "llama_model.model.layers.23.self_attn.v_proj.weight", "llama_model.model.layers.23.self_attn.o_proj.weight", "llama_model.model.layers.23.mlp.gate_proj.weight", "llama_model.model.layers.23.mlp.up_proj.weight", "llama_model.model.layers.23.mlp.down_proj.weight", "llama_model.model.layers.23.input_layernorm.weight", "llama_model.model.layers.23.post_attention_layernorm.weight", "llama_model.model.layers.24.self_attn.q_proj.weight", "llama_model.model.layers.24.self_attn.k_proj.weight", "llama_model.model.layers.24.self_attn.v_proj.weight", "llama_model.model.layers.24.self_attn.o_proj.weight", "llama_model.model.layers.24.mlp.gate_proj.weight", "llama_model.model.layers.24.mlp.up_proj.weight", "llama_model.model.layers.24.mlp.down_proj.weight", "llama_model.model.layers.24.input_layernorm.weight", "llama_model.model.layers.24.post_attention_layernorm.weight", "llama_model.model.layers.25.self_attn.q_proj.weight", "llama_model.model.layers.25.self_attn.k_proj.weight", "llama_model.model.layers.25.self_attn.v_proj.weight", "llama_model.model.layers.25.self_attn.o_proj.weight", "llama_model.model.layers.25.mlp.gate_proj.weight", "llama_model.model.layers.25.mlp.up_proj.weight", "llama_model.model.layers.25.mlp.down_proj.weight", "llama_model.model.layers.25.input_layernorm.weight", "llama_model.model.layers.25.post_attention_layernorm.weight", "llama_model.model.layers.26.self_attn.q_proj.weight", "llama_model.model.layers.26.self_attn.k_proj.weight", "llama_model.model.layers.26.self_attn.v_proj.weight", "llama_model.model.layers.26.self_attn.o_proj.weight", "llama_model.model.layers.26.mlp.gate_proj.weight", "llama_model.model.layers.26.mlp.up_proj.weight", "llama_model.model.layers.26.mlp.down_proj.weight", "llama_model.model.layers.26.input_layernorm.weight", "llama_model.model.layers.26.post_attention_layernorm.weight", "llama_model.model.layers.27.self_attn.q_proj.weight", "llama_model.model.layers.27.self_attn.k_proj.weight", "llama_model.model.layers.27.self_attn.v_proj.weight", "llama_model.model.layers.27.self_attn.o_proj.weight", "llama_model.model.layers.27.mlp.gate_proj.weight", "llama_model.model.layers.27.mlp.up_proj.weight", "llama_model.model.layers.27.mlp.down_proj.weight", "llama_model.model.layers.27.input_layernorm.weight", "llama_model.model.layers.27.post_attention_layernorm.weight", "llama_model.model.layers.28.self_attn.q_proj.weight", "llama_model.model.layers.28.self_attn.k_proj.weight", "llama_model.model.layers.28.self_attn.v_proj.weight", "llama_model.model.layers.28.self_attn.o_proj.weight", "llama_model.model.layers.28.mlp.gate_proj.weight", "llama_model.model.layers.28.mlp.up_proj.weight", "llama_model.model.layers.28.mlp.down_proj.weight", "llama_model.model.layers.28.input_layernorm.weight", "llama_model.model.layers.28.post_attention_layernorm.weight", "llama_model.model.layers.29.self_attn.q_proj.weight", "llama_model.model.layers.29.self_attn.k_proj.weight", "llama_model.model.layers.29.self_attn.v_proj.weight", "llama_model.model.layers.29.self_attn.o_proj.weight", "llama_model.model.layers.29.mlp.gate_proj.weight", "llama_model.model.layers.29.mlp.up_proj.weight", "llama_model.model.layers.29.mlp.down_proj.weight", "llama_model.model.layers.29.input_layernorm.weight", "llama_model.model.layers.29.post_attention_layernorm.weight", "llama_model.model.layers.30.self_attn.q_proj.weight", "llama_model.model.layers.30.self_attn.k_proj.weight", "llama_model.model.layers.30.self_attn.v_proj.weight", "llama_model.model.layers.30.self_attn.o_proj.weight", "llama_model.model.layers.30.mlp.gate_proj.weight", "llama_model.model.layers.30.mlp.up_proj.weight", "llama_model.model.layers.30.mlp.down_proj.weight", "llama_model.model.layers.30.input_layernorm.weight", "llama_model.model.layers.30.post_attention_layernorm.weight", "llama_model.model.layers.31.self_attn.q_proj.weight", "llama_model.model.layers.31.self_attn.k_proj.weight", "llama_model.model.layers.31.self_attn.v_proj.weight", "llama_model.model.layers.31.self_attn.o_proj.weight", "llama_model.model.layers.31.mlp.gate_proj.weight", "llama_model.model.layers.31.mlp.up_proj.weight", "llama_model.model.layers.31.mlp.down_proj.weight", "llama_model.model.layers.31.input_layernorm.weight", "llama_model.model.layers.31.post_attention_layernorm.weight", "llama_model.model.norm.weight", "llama_model.lm_head.weight".