runtime error

Exit code: 1. Reason: [INFO] Đang tải model: Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf ... Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf: 0%| | 0.00/4.68G [00:00<?, ?B/s] Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf: 0%| | 0.00/4.68G [00:02<?, ?B/s] Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf: 9%|▊ | 403M/4.68G [00:03<00:11, 359MB/s] Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf: 32%|███▏ | 1.48G/4.68G [00:05<00:06, 509MB/s] Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf: 59%|█████▊ | 2.75G/4.68G [00:06<00:02, 679MB/s] Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf: 100%|██████████| 4.68G/4.68G [00:06<00:00, 675MB/s] [INFO] Model đã sẵn sàng tại: models/Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf Traceback (most recent call last): File "/app/app.py", line 32, in <module> llm = AutoModelForCausalLM.from_pretrained( model_path_or_repo_id = LOCAL_DIR, ...<5 lines>... local_files_only = True, # Dùng file đã tải, không fetch lại ) File "/usr/local/lib/python3.13/site-packages/ctransformers/hub.py", line 175, in from_pretrained llm = LLM( model_path=model_path, ...<2 lines>... lib=lib, ) File "/usr/local/lib/python3.13/site-packages/ctransformers/llm.py", line 253, in __init__ raise RuntimeError( f"Failed to create LLM '{model_type}' from '{model_path}'." ) RuntimeError: Failed to create LLM 'qwen2' from '/app/models/Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf'.

Container logs: