runtime error

Exit code: 1. Reason: 002.safetensors: 100%|██████████| 2.04G/2.04G [00:08<00:00, 240MB/s] Downloading shards: 50%|█████ | 1/2 [00:08<00:08, 8.58s/it] model-00002-of-00002.safetensors: 0%| | 0.00/1.63G [00:00<?, ?B/s] model-00002-of-00002.safetensors: 4%|▍ | 67.1M/1.63G [00:02<00:53, 29.2MB/s] model-00002-of-00002.safetensors: 29%|██▉ | 470M/1.63G [00:03<00:07, 161MB/s]  model-00002-of-00002.safetensors: 49%|████▉ | 805M/1.63G [00:04<00:03, 217MB/s] model-00002-of-00002.safetensors: 92%|█████████▏| 1.50G/1.63G [00:05<00:00, 368MB/s] model-00002-of-00002.safetensors: 100%|██████████| 1.63G/1.63G [00:05<00:00, 274MB/s] Downloading shards: 100%|██████████| 2/2 [00:14<00:00, 7.07s/it] Downloading shards: 100%|██████████| 2/2 [00:14<00:00, 7.30s/it] Traceback (most recent call last): File "/home/user/app/app.py", line 593, in <module> llm = LLM(mode='offline').init_model('Qwen', 'Qwen/Qwen-1_8B-Chat') File "/home/user/app/LLM/__init__.py", line 40, in init_model llm = Qwen(self.mode, model_path) File "/home/user/app/LLM/Qwen.py", line 19, in __init__ self.model, self.tokenizer = self.init_model(model_path) File "/home/user/app/LLM/Qwen.py", line 23, in init_model model = AutoModelForCausalLM.from_pretrained(path, File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 511, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3091, in from_pretrained ) = cls._load_pretrained_model( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3408, in _load_pretrained_model offload_index = { File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3411, in <dictcomp> if param_device_map[p] == "disk" KeyError: 'lm_head.weight'

Container logs: