runtime error

�████████| 33/33 [01:45<00:00, 3.63s/it] 2023-12-16 05:20:25 | ERROR | stderr |  2023-12-16 05:20:26 | ERROR | stderr | Downloading shards: 100%|██████████| 33/33 [01:45<00:00, 3.20s/it] 2023-12-16 05:20:26 | ERROR | stderr | 2023-12-16 05:20:26 | ERROR | stderr | Traceback (most recent call last): 2023-12-16 05:20:26 | ERROR | stderr | File "/home/user/app/app.py", line 388, in <module> 2023-12-16 05:20:26 | ERROR | stderr | model = ModelWorker(args.model_path, None, None, args.load_8bit, args.load_4bit, args.device) 2023-12-16 05:20:26 | ERROR | stderr | File "/home/user/app/model_worker.py", line 45, in __init__ 2023-12-16 05:20:26 | ERROR | stderr | self.tokenizer, self.model, self.image_processor, self.context_len = load_pretrained_model( 2023-12-16 05:20:26 | ERROR | stderr | File "/home/user/app/mplug_owl2/model/builder.py", line 106, in load_pretrained_model 2023-12-16 05:20:26 | ERROR | stderr | model = AutoModelForCausalLM.from_pretrained(model_path, low_cpu_mem_usage=True, **kwargs) 2023-12-16 05:20:26 | ERROR | stderr | File "/home/user/.local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 493, in from_pretrained 2023-12-16 05:20:26 | ERROR | stderr | return model_class.from_pretrained( 2023-12-16 05:20:26 | ERROR | stderr | File "/home/user/.local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2903, in from_pretrained 2023-12-16 05:20:26 | ERROR | stderr | ) = cls._load_pretrained_model( 2023-12-16 05:20:26 | ERROR | stderr | File "/home/user/.local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3002, in _load_pretrained_model 2023-12-16 05:20:26 | ERROR | stderr | raise ValueError( 2023-12-16 05:20:26 | ERROR | stderr | ValueError: The current `device_map` had weights offloaded to the disk. Please provide an `offload_folder` for them. Alternatively, make sure you have `safetensors` installed if the model you are using offers the weights in this format.

Container logs: