We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
followed the instruction in https://github.com/lm-sys/FastChat/blob/main/docs/gptq.md. And load the model. But there is an error when load the model using python3 -m fastchat.serve.model_worker --model-path models/llama-2-7B-GPTQ --gptq-wbits 4 --gptq-groupsize 128: 2024-02-12 21:31:13 | INFO | stdout | Loading model ... 2024-02-12 21:31:13 | ERROR | stderr | Traceback (most recent call last): 2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/runpy.py", line 196, in _run_module_as_main 2024-02-12 21:31:13 | ERROR | stderr | return _run_code(code, main_globals, None, 2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/runpy.py", line 86, in _run_code 2024-02-12 21:31:13 | ERROR | stderr | exec(code, run_globals) 2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/site-packages/fastchat/serve/model_worker.py", line 375, in 2024-02-12 21:31:13 | ERROR | stderr | args, worker = create_model_worker() 2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/site-packages/fastchat/serve/model_worker.py", line 346, in create_model_worker 2024-02-12 21:31:13 | ERROR | stderr | worker = ModelWorker( 2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/site-packages/fastchat/serve/model_worker.py", line 77, in init 2024-02-12 21:31:13 | ERROR | stderr | self.model, self.tokenizer = load_model( 2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/site-packages/fastchat/model/model_adapter.py", line 310, in load_model 2024-02-12 21:31:13 | ERROR | stderr | model, tokenizer = load_gptq_quantized(model_path, gptq_config) 2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/site-packages/fastchat/modules/gptq.py", line 55, in load_gptq_quantized 2024-02-12 21:31:13 | ERROR | stderr | model = load_quant( 2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/llm/GPTQ-for-LLaMa/llama.py", line 308, in load_quant 2024-02-12 21:31:13 | ERROR | stderr | model.load_state_dict(safe_load(checkpoint)) 2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2152, in load_state_dict 2024-02-12 21:31:13 | ERROR | stderr | raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( 2024-02-12 21:31:13 | ERROR | stderr | RuntimeError: Error(s) in loading state_dict for LlamaForCausalLM: 2024-02-12 21:31:13 | ERROR | stderr | Unexpected key(s) in state_dict: "model.layers.0.self_attn.rotary_emb.inv_freq", "model.layers.0.self_attn.k_proj.bias", "model.layers.0.self_attn.o_proj.bias", "model.layers.0.self_attn.q_proj.bias", "model.layers.0.self_attn.v_proj.bias", "model.layers.0.mlp.down_proj.bias", "model.layers.0.mlp.gate_proj.bias", "model.layers.0.mlp.up_proj.bias", "model.layers.1.self_attn.rotary_emb.inv_freq", "model.layers.1.self_attn.k_proj.bias", "model.layers.1.self_attn.o_proj.bias", "model.layers.1.self_attn.q_proj.bias", "model.layers.1.self_attn.v_proj.bias", "model.layers.1.mlp.down_proj.bias", "model.layers.1.mlp.gate_proj.bias", "model.layers.1.mlp.up_proj.bias", "model.layers.2.self_attn.rotary_emb.inv_freq", "model.layers.2.self_attn.k_proj.bias", "model.layers.2.self_attn.o_proj.bias", "model.layers.2.self_attn.q_proj.bias", "model.layers.2.self_attn.v_proj.bias", "model.layers.2.mlp.down_proj.bias", "model.layers.2.mlp.gate_proj.bias", "model.layers.2.mlp.up_proj.bias", "model.layers.3.self_attn.rotary_emb.inv_freq", "model.layers.3.self_attn.k_proj.bias", "model.layers.3.self_attn.o_proj.bias", "model.layers.3.self_attn.q_proj.bias", "model.layers.3.self_attn.v_proj.bias", "model.layers.3.mlp.down_proj.bias", "model.layers.3.mlp.gate_proj.bias", "model.layers.3.mlp.up_proj.bias", "model.layers.4.self_attn.rotary_emb.inv_freq", "model.layers.4.self_attn.k_proj.bias", "model.layers.4.self_attn.o_proj.bias", "model.layers.4.self_attn.q_proj.bias", "model.layers.4.self_attn.v_proj.bias", "model.layers.4.mlp.down_proj.bias", "model.layers.4.mlp.gate_proj.bias", "model.layers.4.mlp.up_proj.bias", "model.layers.5.self_attn.rotary_emb.inv_freq", "model.layers.5.self_attn.k_proj.bias", "model.layers.5.self_attn.o_proj.bias", "model.layers.5.self_attn.q_proj.bias", "model.layers.5.self_attn.v_proj.bias", "model.layers.5.mlp.down_proj.bias", "model.layers.5.mlp.gate_proj.bias", "model.layers.5.mlp.up_proj.bias", "model.layers.6.self_attn.rotary_emb.inv_freq", "model.layers.6.self_attn.k_proj.bias", "model.layers.6.self_attn.o_proj.bias", "model.layers.6.self_attn.q_proj.bias", "model.layers.6.self_attn.v_proj.bias", "model.layers.6.mlp.down_proj.bias", "model.layers.6.mlp.gate_proj.bias", "model.layers.6.mlp.up_proj.bias", "model.layers.7.self_attn.rotary_emb.inv_freq", "model.layers.7.self_attn.k_proj.bias", "model.layers.7.self_attn.o_proj.bias", "model.layers.7.self_attn.q_proj.bias", "model.layers.7.self_attn.v_proj.bias", "model.layers.7.mlp.down_proj.bias", "model.layers.7.mlp.gate_proj.bias", "model.layers.7.mlp.up_proj.bias", "model.layers.8.self_attn.rotary_emb.inv_freq", "model.layers.8.self_attn.k_proj.bias", "model.layers.8.self_attn.o_proj.bias", "model.layers.8.self_attn.q_proj.bias", "model.layers.8.self_attn.v_proj.bias", "model.layers.8.mlp.down_proj.bias", "model.layers.8.mlp.gate_proj.bias", "model.layers.8.mlp.up_proj.bias", "model.layers.9.self_attn.rotary_emb.inv_freq", "model.layers.9.self_attn.k_proj.bias", "model.layers.9.self_attn.o_proj.bias", "model.layers.9.self_attn.q_proj.bias", "model.layers.9.self_attn.v_proj.bias", "model.layers.9.mlp.down_proj.bias", "model.layers.9.mlp.gate_proj.bias", "model.layers.9.mlp.up_proj.bias", "model.layers.10.self_attn.rotary_emb.inv_freq", "model.layers.10.self_attn.k_proj.bias", "model.layers.10.self_attn.o_proj.bias", "model.layers.10.self_attn.q_proj.bias", "model.layers.10.self_attn.v_proj.bias", "model.layers.10.mlp.down_proj.bias", "model.layers.10.mlp.gate_proj.bias", "model.layers.10.mlp.up_proj.bias", "model.layers.11.self_attn.rotary_emb.inv_freq", "model.layers.11.self_attn.k_proj.bias", "model.layers.11.self_attn.o_proj.bias", "model.layers.11.self_attn.q_proj.bias", "model.layers.11.self_attn.v_proj.bias", "model.layers.11.mlp.down_proj.bias", "model.layers.11.mlp.gate_proj.bias", "model.layers.11.mlp.up_proj.bias", "model.layers.12.self_attn.rotary_emb.inv_freq", "model.layers.12.self_attn.k_proj.bias", "model.layers.12.self_attn.o_proj.bias", "model.layers.12.self_attn.q_proj.bias", "model.layers.12.self_attn.v_proj.bias", "model.layers.12.mlp.down_proj.bias", "model.layers.12.mlp.gate_proj.bias", "model.layers.12.mlp.up_proj.bias", "model.layers.13.self_attn.rotary_emb.inv_freq", "model.layers.13.self_attn.k_proj.bias", "model.layers.13.self_attn.o_proj.bias", "model.layers.13.self_attn.q_proj.bias", "model.layers.13.self_attn.v_proj.bias", "model.layers.13.mlp.down_proj.bias", "model.layers.13.mlp.gate_proj.bias", "model.layers.13.mlp.up_proj.bias", "model.layers.14.self_attn.rotary_emb.inv_freq", "model.layers.14.self_attn.k_proj.bias", "model.layers.14.self_attn.o_proj.bias", "model.layers.14.self_attn.q_proj.bias", "model.layers.14.self_attn.v_proj.bias", "model.layers.14.mlp.down_proj.bias", "model.layers.14.mlp.gate_proj.bias", "model.layers.14.mlp.up_proj.bias", "model.layers.15.self_attn.rotary_emb.inv_freq", "model.layers.15.self_attn.k_proj.bias", "model.layers.15.self_attn.o_proj.bias", "model.layers.15.self_attn.q_proj.bias", "model.layers.15.self_attn.v_proj.bias", "model.layers.15.mlp.down_proj.bias", "model.layers.15.mlp.gate_proj.bias", "model.layers.15.mlp.up_proj.bias", "model.layers.16.self_attn.rotary_emb.inv_freq", "model.layers.16.self_attn.k_proj.bias", "model.layers.16.self_attn.o_proj.bias", "model.layers.16.self_attn.q_proj.bias", "model.layers.16.self_attn.v_proj.bias", "model.layers.16.mlp.down_proj.bias", "model.layers.16.mlp.gate_proj.bias", "model.layers.16.mlp.up_proj.bias", "model.layers.17.self_attn.rotary_emb.inv_freq", "model.layers.17.self_attn.k_proj.bias", "model.layers.17.self_attn.o_proj.bias", "model.layers.17.self_attn.q_proj.bias", "model.layers.17.self_attn.v_proj.bias", "model.layers.17.mlp.down_proj.bias", "model.layers.17.mlp.gate_proj.bias", "model.layers.17.mlp.up_proj.bias", "model.layers.18.self_attn.rotary_emb.inv_freq", "model.layers.18.self_attn.k_proj.bias", "model.layers.18.self_attn.o_proj.bias", "model.layers.18.self_attn.q_proj.bias", "model.layers.18.self_attn.v_proj.bias", "model.layers.18.mlp.down_proj.bias", "model.layers.18.mlp.gate_proj.bias", "model.layers.18.mlp.up_proj.bias", "model.layers.19.self_attn.rotary_emb.inv_freq", "model.layers.19.self_attn.k_proj.bias", "model.layers.19.self_attn.o_proj.bias", "model.layers.19.self_attn.q_proj.bias", "model.layers.19.self_attn.v_proj.bias", "model.layers.19.mlp.down_proj.bias", "model.layers.19.mlp.gate_proj.bias", "model.layers.19.mlp.up_proj.bias", "model.layers.20.self_attn.rotary_emb.inv_freq", "model.layers.20.self_attn.k_proj.bias", "model.layers.20.self_attn.o_proj.bias", "model.layers.20.self_attn.q_proj.bias", "model.layers.20.self_attn.v_proj.bias", "model.layers.20.mlp.down_proj.bias", "model.layers.20.mlp.gate_proj.bias", "model.layers.20.mlp.up_proj.bias", "model.layers.21.self_attn.rotary_emb.inv_freq", "model.layers.21.self_attn.k_proj.bias", "model.layers.21.self_attn.o_proj.bias", "model.layers.21.self_attn.q_proj.bias", "model.layers.21.self_attn.v_proj.bias", "model.layers.21.mlp.down_proj.bias", "model.layers.21.mlp.gate_proj.bias", "model.layers.21.mlp.up_proj.bias", "model.layers.22.self_attn.rotary_emb.inv_freq", "model.layers.22.self_attn.k_proj.bias", "model.layers.22.self_attn.o_proj.bias", "model.layers.22.self_attn.q_proj.bias", "model.layers.22.self_attn.v_proj.bias", "model.layers.22.mlp.down_proj.bias", "model.layers.22.mlp.gate_proj.bias", "model.layers.22.mlp.up_proj.bias", "model.layers.23.self_attn.rotary_emb.inv_freq", "model.layers.23.self_attn.k_proj.bias", "model.layers.23.self_attn.o_proj.bias", "model.layers.23.self_attn.q_proj.bias", "model.layers.23.self_attn.v_proj.bias", "model.layers.23.mlp.down_proj.bias", "model.layers.23.mlp.gate_proj.bias", "model.layers.23.mlp.up_proj.bias", "model.layers.24.self_attn.rotary_emb.inv_freq", "model.layers.24.self_attn.k_proj.bias", "model.layers.24.self_attn.o_proj.bias", "model.layers.24.self_attn.q_proj.bias", "model.layers.24.self_attn.v_proj.bias", "model.layers.24.mlp.down_proj.bias", "model.layers.24.mlp.gate_proj.bias", "model.layers.24.mlp.up_proj.bias", "model.layers.25.self_attn.rotary_emb.inv_freq", "model.layers.25.self_attn.k_proj.bias", "model.layers.25.self_attn.o_proj.bias", "model.layers.25.self_attn.q_proj.bias", "model.layers.25.self_attn.v_proj.bias", "model.layers.25.mlp.down_proj.bias", "model.layers.25.mlp.gate_proj.bias", "model.layers.25.mlp.up_proj.bias", "model.layers.26.self_attn.rotary_emb.inv_freq", "model.layers.26.self_attn.k_proj.bias", "model.layers.26.self_attn.o_proj.bias", "model.layers.26.self_attn.q_proj.bias", "model.layers.26.self_attn.v_proj.bias", "model.layers.26.mlp.down_proj.bias", "model.layers.26.mlp.gate_proj.bias", "model.layers.26.mlp.up_proj.bias", "model.layers.27.self_attn.rotary_emb.inv_freq", "model.layers.27.self_attn.k_proj.bias", "model.layers.27.self_attn.o_proj.bias", "model.layers.27.self_attn.q_proj.bias", "model.layers.27.self_attn.v_proj.bias", "model.layers.27.mlp.down_proj.bias", "model.layers.27.mlp.gate_proj.bias", "model.layers.27.mlp.up_proj.bias", "model.layers.28.self_attn.rotary_emb.inv_freq", "model.layers.28.self_attn.k_proj.bias", "model.layers.28.self_attn.o_proj.bias", "model.layers.28.self_attn.q_proj.bias", "model.layers.28.self_attn.v_proj.bias", "model.layers.28.mlp.down_proj.bias", "model.layers.28.mlp.gate_proj.bias", "model.layers.28.mlp.up_proj.bias", "model.layers.29.self_attn.rotary_emb.inv_freq", "model.layers.29.self_attn.k_proj.bias", "model.layers.29.self_attn.o_proj.bias", "model.layers.29.self_attn.q_proj.bias", "model.layers.29.self_attn.v_proj.bias", "model.layers.29.mlp.down_proj.bias", "model.layers.29.mlp.gate_proj.bias", "model.layers.29.mlp.up_proj.bias", "model.layers.30.self_attn.rotary_emb.inv_freq", "model.layers.30.self_attn.k_proj.bias", "model.layers.30.self_attn.o_proj.bias", "model.layers.30.self_attn.q_proj.bias", "model.layers.30.self_attn.v_proj.bias", "model.layers.30.mlp.down_proj.bias", "model.layers.30.mlp.gate_proj.bias", "model.layers.30.mlp.up_proj.bias", "model.layers.31.self_attn.rotary_emb.inv_freq", "model.layers.31.self_attn.k_proj.bias", "model.layers.31.self_attn.o_proj.bias", "model.layers.31.self_attn.q_proj.bias", "model.layers.31.self_attn.v_proj.bias", "model.layers.31.mlp.down_proj.bias", "model.layers.31.mlp.gate_proj.bias", "model.layers.31.mlp.up_proj.bias".
The text was updated successfully, but these errors were encountered:
No branches or pull requests
followed the instruction in https://github.com/lm-sys/FastChat/blob/main/docs/gptq.md. And load the model.
But there is an error when load the model using python3 -m fastchat.serve.model_worker --model-path models/llama-2-7B-GPTQ --gptq-wbits 4 --gptq-groupsize 128:
2024-02-12 21:31:13 | INFO | stdout | Loading model ...
2024-02-12 21:31:13 | ERROR | stderr | Traceback (most recent call last):
2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/runpy.py", line 196, in _run_module_as_main
2024-02-12 21:31:13 | ERROR | stderr | return _run_code(code, main_globals, None,
2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/runpy.py", line 86, in _run_code
2024-02-12 21:31:13 | ERROR | stderr | exec(code, run_globals)
2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/site-packages/fastchat/serve/model_worker.py", line 375, in
2024-02-12 21:31:13 | ERROR | stderr | args, worker = create_model_worker()
2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/site-packages/fastchat/serve/model_worker.py", line 346, in create_model_worker
2024-02-12 21:31:13 | ERROR | stderr | worker = ModelWorker(
2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/site-packages/fastchat/serve/model_worker.py", line 77, in init
2024-02-12 21:31:13 | ERROR | stderr | self.model, self.tokenizer = load_model(
2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/site-packages/fastchat/model/model_adapter.py", line 310, in load_model
2024-02-12 21:31:13 | ERROR | stderr | model, tokenizer = load_gptq_quantized(model_path, gptq_config)
2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/site-packages/fastchat/modules/gptq.py", line 55, in load_gptq_quantized
2024-02-12 21:31:13 | ERROR | stderr | model = load_quant(
2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/llm/GPTQ-for-LLaMa/llama.py", line 308, in load_quant
2024-02-12 21:31:13 | ERROR | stderr | model.load_state_dict(safe_load(checkpoint))
2024-02-12 21:31:13 | ERROR | stderr | File "/home/kyrie/miniconda3/envs/llm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2152, in load_state_dict
2024-02-12 21:31:13 | ERROR | stderr | raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
2024-02-12 21:31:13 | ERROR | stderr | RuntimeError: Error(s) in loading state_dict for LlamaForCausalLM:
2024-02-12 21:31:13 | ERROR | stderr | Unexpected key(s) in state_dict: "model.layers.0.self_attn.rotary_emb.inv_freq", "model.layers.0.self_attn.k_proj.bias", "model.layers.0.self_attn.o_proj.bias", "model.layers.0.self_attn.q_proj.bias", "model.layers.0.self_attn.v_proj.bias", "model.layers.0.mlp.down_proj.bias", "model.layers.0.mlp.gate_proj.bias", "model.layers.0.mlp.up_proj.bias", "model.layers.1.self_attn.rotary_emb.inv_freq", "model.layers.1.self_attn.k_proj.bias", "model.layers.1.self_attn.o_proj.bias", "model.layers.1.self_attn.q_proj.bias", "model.layers.1.self_attn.v_proj.bias", "model.layers.1.mlp.down_proj.bias", "model.layers.1.mlp.gate_proj.bias", "model.layers.1.mlp.up_proj.bias", "model.layers.2.self_attn.rotary_emb.inv_freq", "model.layers.2.self_attn.k_proj.bias", "model.layers.2.self_attn.o_proj.bias", "model.layers.2.self_attn.q_proj.bias", "model.layers.2.self_attn.v_proj.bias", "model.layers.2.mlp.down_proj.bias", "model.layers.2.mlp.gate_proj.bias", "model.layers.2.mlp.up_proj.bias", "model.layers.3.self_attn.rotary_emb.inv_freq", "model.layers.3.self_attn.k_proj.bias", "model.layers.3.self_attn.o_proj.bias", "model.layers.3.self_attn.q_proj.bias", "model.layers.3.self_attn.v_proj.bias", "model.layers.3.mlp.down_proj.bias", "model.layers.3.mlp.gate_proj.bias", "model.layers.3.mlp.up_proj.bias", "model.layers.4.self_attn.rotary_emb.inv_freq", "model.layers.4.self_attn.k_proj.bias", "model.layers.4.self_attn.o_proj.bias", "model.layers.4.self_attn.q_proj.bias", "model.layers.4.self_attn.v_proj.bias", "model.layers.4.mlp.down_proj.bias", "model.layers.4.mlp.gate_proj.bias", "model.layers.4.mlp.up_proj.bias", "model.layers.5.self_attn.rotary_emb.inv_freq", "model.layers.5.self_attn.k_proj.bias", "model.layers.5.self_attn.o_proj.bias", "model.layers.5.self_attn.q_proj.bias", "model.layers.5.self_attn.v_proj.bias", "model.layers.5.mlp.down_proj.bias", "model.layers.5.mlp.gate_proj.bias", "model.layers.5.mlp.up_proj.bias", "model.layers.6.self_attn.rotary_emb.inv_freq", "model.layers.6.self_attn.k_proj.bias", "model.layers.6.self_attn.o_proj.bias", "model.layers.6.self_attn.q_proj.bias", "model.layers.6.self_attn.v_proj.bias", "model.layers.6.mlp.down_proj.bias", "model.layers.6.mlp.gate_proj.bias", "model.layers.6.mlp.up_proj.bias", "model.layers.7.self_attn.rotary_emb.inv_freq", "model.layers.7.self_attn.k_proj.bias", "model.layers.7.self_attn.o_proj.bias", "model.layers.7.self_attn.q_proj.bias", "model.layers.7.self_attn.v_proj.bias", "model.layers.7.mlp.down_proj.bias", "model.layers.7.mlp.gate_proj.bias", "model.layers.7.mlp.up_proj.bias", "model.layers.8.self_attn.rotary_emb.inv_freq", "model.layers.8.self_attn.k_proj.bias", "model.layers.8.self_attn.o_proj.bias", "model.layers.8.self_attn.q_proj.bias", "model.layers.8.self_attn.v_proj.bias", "model.layers.8.mlp.down_proj.bias", "model.layers.8.mlp.gate_proj.bias", "model.layers.8.mlp.up_proj.bias", "model.layers.9.self_attn.rotary_emb.inv_freq", "model.layers.9.self_attn.k_proj.bias", "model.layers.9.self_attn.o_proj.bias", "model.layers.9.self_attn.q_proj.bias", "model.layers.9.self_attn.v_proj.bias", "model.layers.9.mlp.down_proj.bias", "model.layers.9.mlp.gate_proj.bias", "model.layers.9.mlp.up_proj.bias", "model.layers.10.self_attn.rotary_emb.inv_freq", "model.layers.10.self_attn.k_proj.bias", "model.layers.10.self_attn.o_proj.bias", "model.layers.10.self_attn.q_proj.bias", "model.layers.10.self_attn.v_proj.bias", "model.layers.10.mlp.down_proj.bias", "model.layers.10.mlp.gate_proj.bias", "model.layers.10.mlp.up_proj.bias", "model.layers.11.self_attn.rotary_emb.inv_freq", "model.layers.11.self_attn.k_proj.bias", "model.layers.11.self_attn.o_proj.bias", "model.layers.11.self_attn.q_proj.bias", "model.layers.11.self_attn.v_proj.bias", "model.layers.11.mlp.down_proj.bias", "model.layers.11.mlp.gate_proj.bias", "model.layers.11.mlp.up_proj.bias", "model.layers.12.self_attn.rotary_emb.inv_freq", "model.layers.12.self_attn.k_proj.bias", "model.layers.12.self_attn.o_proj.bias", "model.layers.12.self_attn.q_proj.bias", "model.layers.12.self_attn.v_proj.bias", "model.layers.12.mlp.down_proj.bias", "model.layers.12.mlp.gate_proj.bias", "model.layers.12.mlp.up_proj.bias", "model.layers.13.self_attn.rotary_emb.inv_freq", "model.layers.13.self_attn.k_proj.bias", "model.layers.13.self_attn.o_proj.bias", "model.layers.13.self_attn.q_proj.bias", "model.layers.13.self_attn.v_proj.bias", "model.layers.13.mlp.down_proj.bias", "model.layers.13.mlp.gate_proj.bias", "model.layers.13.mlp.up_proj.bias", "model.layers.14.self_attn.rotary_emb.inv_freq", "model.layers.14.self_attn.k_proj.bias", "model.layers.14.self_attn.o_proj.bias", "model.layers.14.self_attn.q_proj.bias", "model.layers.14.self_attn.v_proj.bias", "model.layers.14.mlp.down_proj.bias", "model.layers.14.mlp.gate_proj.bias", "model.layers.14.mlp.up_proj.bias", "model.layers.15.self_attn.rotary_emb.inv_freq", "model.layers.15.self_attn.k_proj.bias", "model.layers.15.self_attn.o_proj.bias", "model.layers.15.self_attn.q_proj.bias", "model.layers.15.self_attn.v_proj.bias", "model.layers.15.mlp.down_proj.bias", "model.layers.15.mlp.gate_proj.bias", "model.layers.15.mlp.up_proj.bias", "model.layers.16.self_attn.rotary_emb.inv_freq", "model.layers.16.self_attn.k_proj.bias", "model.layers.16.self_attn.o_proj.bias", "model.layers.16.self_attn.q_proj.bias", "model.layers.16.self_attn.v_proj.bias", "model.layers.16.mlp.down_proj.bias", "model.layers.16.mlp.gate_proj.bias", "model.layers.16.mlp.up_proj.bias", "model.layers.17.self_attn.rotary_emb.inv_freq", "model.layers.17.self_attn.k_proj.bias", "model.layers.17.self_attn.o_proj.bias", "model.layers.17.self_attn.q_proj.bias", "model.layers.17.self_attn.v_proj.bias", "model.layers.17.mlp.down_proj.bias", "model.layers.17.mlp.gate_proj.bias", "model.layers.17.mlp.up_proj.bias", "model.layers.18.self_attn.rotary_emb.inv_freq", "model.layers.18.self_attn.k_proj.bias", "model.layers.18.self_attn.o_proj.bias", "model.layers.18.self_attn.q_proj.bias", "model.layers.18.self_attn.v_proj.bias", "model.layers.18.mlp.down_proj.bias", "model.layers.18.mlp.gate_proj.bias", "model.layers.18.mlp.up_proj.bias", "model.layers.19.self_attn.rotary_emb.inv_freq", "model.layers.19.self_attn.k_proj.bias", "model.layers.19.self_attn.o_proj.bias", "model.layers.19.self_attn.q_proj.bias", "model.layers.19.self_attn.v_proj.bias", "model.layers.19.mlp.down_proj.bias", "model.layers.19.mlp.gate_proj.bias", "model.layers.19.mlp.up_proj.bias", "model.layers.20.self_attn.rotary_emb.inv_freq", "model.layers.20.self_attn.k_proj.bias", "model.layers.20.self_attn.o_proj.bias", "model.layers.20.self_attn.q_proj.bias", "model.layers.20.self_attn.v_proj.bias", "model.layers.20.mlp.down_proj.bias", "model.layers.20.mlp.gate_proj.bias", "model.layers.20.mlp.up_proj.bias", "model.layers.21.self_attn.rotary_emb.inv_freq", "model.layers.21.self_attn.k_proj.bias", "model.layers.21.self_attn.o_proj.bias", "model.layers.21.self_attn.q_proj.bias", "model.layers.21.self_attn.v_proj.bias", "model.layers.21.mlp.down_proj.bias", "model.layers.21.mlp.gate_proj.bias", "model.layers.21.mlp.up_proj.bias", "model.layers.22.self_attn.rotary_emb.inv_freq", "model.layers.22.self_attn.k_proj.bias", "model.layers.22.self_attn.o_proj.bias", "model.layers.22.self_attn.q_proj.bias", "model.layers.22.self_attn.v_proj.bias", "model.layers.22.mlp.down_proj.bias", "model.layers.22.mlp.gate_proj.bias", "model.layers.22.mlp.up_proj.bias", "model.layers.23.self_attn.rotary_emb.inv_freq", "model.layers.23.self_attn.k_proj.bias", "model.layers.23.self_attn.o_proj.bias", "model.layers.23.self_attn.q_proj.bias", "model.layers.23.self_attn.v_proj.bias", "model.layers.23.mlp.down_proj.bias", "model.layers.23.mlp.gate_proj.bias", "model.layers.23.mlp.up_proj.bias", "model.layers.24.self_attn.rotary_emb.inv_freq", "model.layers.24.self_attn.k_proj.bias", "model.layers.24.self_attn.o_proj.bias", "model.layers.24.self_attn.q_proj.bias", "model.layers.24.self_attn.v_proj.bias", "model.layers.24.mlp.down_proj.bias", "model.layers.24.mlp.gate_proj.bias", "model.layers.24.mlp.up_proj.bias", "model.layers.25.self_attn.rotary_emb.inv_freq", "model.layers.25.self_attn.k_proj.bias", "model.layers.25.self_attn.o_proj.bias", "model.layers.25.self_attn.q_proj.bias", "model.layers.25.self_attn.v_proj.bias", "model.layers.25.mlp.down_proj.bias", "model.layers.25.mlp.gate_proj.bias", "model.layers.25.mlp.up_proj.bias", "model.layers.26.self_attn.rotary_emb.inv_freq", "model.layers.26.self_attn.k_proj.bias", "model.layers.26.self_attn.o_proj.bias", "model.layers.26.self_attn.q_proj.bias", "model.layers.26.self_attn.v_proj.bias", "model.layers.26.mlp.down_proj.bias", "model.layers.26.mlp.gate_proj.bias", "model.layers.26.mlp.up_proj.bias", "model.layers.27.self_attn.rotary_emb.inv_freq", "model.layers.27.self_attn.k_proj.bias", "model.layers.27.self_attn.o_proj.bias", "model.layers.27.self_attn.q_proj.bias", "model.layers.27.self_attn.v_proj.bias", "model.layers.27.mlp.down_proj.bias", "model.layers.27.mlp.gate_proj.bias", "model.layers.27.mlp.up_proj.bias", "model.layers.28.self_attn.rotary_emb.inv_freq", "model.layers.28.self_attn.k_proj.bias", "model.layers.28.self_attn.o_proj.bias", "model.layers.28.self_attn.q_proj.bias", "model.layers.28.self_attn.v_proj.bias", "model.layers.28.mlp.down_proj.bias", "model.layers.28.mlp.gate_proj.bias", "model.layers.28.mlp.up_proj.bias", "model.layers.29.self_attn.rotary_emb.inv_freq", "model.layers.29.self_attn.k_proj.bias", "model.layers.29.self_attn.o_proj.bias", "model.layers.29.self_attn.q_proj.bias", "model.layers.29.self_attn.v_proj.bias", "model.layers.29.mlp.down_proj.bias", "model.layers.29.mlp.gate_proj.bias", "model.layers.29.mlp.up_proj.bias", "model.layers.30.self_attn.rotary_emb.inv_freq", "model.layers.30.self_attn.k_proj.bias", "model.layers.30.self_attn.o_proj.bias", "model.layers.30.self_attn.q_proj.bias", "model.layers.30.self_attn.v_proj.bias", "model.layers.30.mlp.down_proj.bias", "model.layers.30.mlp.gate_proj.bias", "model.layers.30.mlp.up_proj.bias", "model.layers.31.self_attn.rotary_emb.inv_freq", "model.layers.31.self_attn.k_proj.bias", "model.layers.31.self_attn.o_proj.bias", "model.layers.31.self_attn.q_proj.bias", "model.layers.31.self_attn.v_proj.bias", "model.layers.31.mlp.down_proj.bias", "model.layers.31.mlp.gate_proj.bias", "model.layers.31.mlp.up_proj.bias".
The text was updated successfully, but these errors were encountered: