runtime error

Exit code: 1. Reason: otal...): 97%|█████████▋| 45.7G/47.1G [02:12<00:03, 407MB/s] Fetching 10 files: 90%|█████████ | 9/10 [02:12<00:11, 11.58s/it]  Fetching 10 files: 100%|██████████| 10/10 [02:12<00:00, 13.29s/it] Download complete: 100%|██████████| 47.1G/47.1G [02:12<00:00, 407MB/s]  Download complete: 100%|██████████| 47.1G/47.1G [02:13<00:00, 352MB/s] Traceback (most recent call last): File "/home/user/app/app.py", line 238, in <module> model, tokenizer = initialize_model() File "/home/user/app/app.py", line 141, in initialize_model model = AutoModelForCausalLM.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 406, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4327, in from_pretrained loading_info, disk_offload_index = cls._load_pretrained_model(model, state_dict, checkpoint_files, load_config) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4408, in _load_pretrained_model caching_allocator_warmup(model, expanded_device_map, load_config.hf_quantizer) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 5058, in caching_allocator_warmup free_device_memory, total_device_memory = accelerator_module.mem_get_info(index) File "/usr/local/lib/python3.10/site-packages/torch/cuda/memory.py", line 847, in mem_get_info return torch.cuda.cudart().cudaMemGetInfo(device) File "/usr/local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 568, in cudart _lazy_init() File "/usr/local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 491, in _lazy_init torch._C._cuda_init() 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: