runtime error

Exit code: 1. Reason: app/app.py", line 417, in <module> 2025-05-19 12:55:22 | ERROR | stderr | model = ModelWorker(args.model_path, None, None, 2025-05-19 12:55:22 | ERROR | stderr | File "/home/user/app/model_worker.py", line 63, in __init__ 2025-05-19 12:55:22 | ERROR | stderr | self.tokenizer, self.model, _, self.context_len = load_pretrained_model( 2025-05-19 12:55:22 | ERROR | stderr | File "/home/user/app/mplug_docowl/model/builder.py", line 55, in load_pretrained_model 2025-05-19 12:55:22 | ERROR | stderr | model = MPLUGDocOwlLlamaForCausalLM.from_pretrained(model_path, low_cpu_mem_usage=True, **kwargs) 2025-05-19 12:55:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2903, in from_pretrained 2025-05-19 12:55:22 | ERROR | stderr | ) = cls._load_pretrained_model( 2025-05-19 12:55:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3260, in _load_pretrained_model 2025-05-19 12:55:22 | ERROR | stderr | new_error_msgs, offload_index, state_dict_index = _load_state_dict_into_meta_model( 2025-05-19 12:55:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 717, in _load_state_dict_into_meta_model 2025-05-19 12:55:22 | ERROR | stderr | set_module_tensor_to_device(model, param_name, param_device, **set_module_kwargs) 2025-05-19 12:55:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/accelerate/utils/modeling.py", line 298, in set_module_tensor_to_device 2025-05-19 12:55:22 | ERROR | stderr | new_value = value.to(device) 2025-05-19 12:55:22 | ERROR | stderr | File "/usr/local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 293, in _lazy_init 2025-05-19 12:55:22 | ERROR | stderr | torch._C._cuda_init() 2025-05-19 12:55:22 | ERROR | stderr | RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx

Container logs: