runtime error

Exit code: 1. Reason: ors: 100%|█████████▉| 4.92G/4.92G [00:10<00:00, 473MB/s] Downloading shards: 75%|███████▌ | 3/4 [00:30<00:10, 10.28s/it] model-00004-of-00004.safetensors: 0%| | 0.00/2.16G [00:00<?, ?B/s] model-00004-of-00004.safetensors: 1%|▏ | 31.5M/2.16G [00:01<01:12, 29.5MB/s] model-00004-of-00004.safetensors: 11%|█ | 241M/2.16G [00:02<00:14, 133MB/s]  model-00004-of-00004.safetensors: 34%|███▍ | 734M/2.16G [00:03<00:04, 294MB/s] model-00004-of-00004.safetensors: 62%|██████▏ | 1.34G/2.16G [00:04<00:01, 416MB/s] model-00004-of-00004.safetensors: 100%|█████████▉| 2.16G/2.16G [00:05<00:00, 415MB/s] Downloading shards: 100%|██████████| 4/4 [00:35<00:00, 8.39s/it] Downloading shards: 100%|██████████| 4/4 [00:35<00:00, 8.97s/it] Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s] Traceback (most recent call last): File "/home/user/app/app.py", line 43, in <module> model = LlavaForConditionalGeneration.from_pretrained(MODEL_PATH, torch_dtype="bfloat16", device_map=0) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4014, in from_pretrained ) = cls._load_pretrained_model( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4502, in _load_pretrained_model new_error_msgs, offload_index, state_dict_index = _load_state_dict_into_meta_model( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 973, in _load_state_dict_into_meta_model set_module_tensor_to_device(model, param_name, param_device, **set_module_kwargs) File "/usr/local/lib/python3.10/site-packages/accelerate/utils/modeling.py", line 304, in set_module_tensor_to_device and torch.device(device).type == "cuda" RuntimeError: Cannot access accelerator device when none is available.

Container logs: