runtime error

Exit code: 1. Reason: G [00:04<00:02, 782MB/s] model-00001-of-00002.safetensors: 78%|███████▊ | 3.88G/5.00G [00:05<00:01, 842MB/s] model-00001-of-00002.safetensors: 95%|█████████▍| 4.75G/5.00G [00:06<00:00, 826MB/s] model-00001-of-00002.safetensors: 100%|█████████▉| 5.00G/5.00G [00:07<00:00, 707MB/s] Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.36s/it] model-00002-of-00002.safetensors: 0%| | 0.00/2.51G [00:00<?, ?B/s] model-00002-of-00002.safetensors: 31%|███ | 776M/2.51G [00:01<00:02, 750MB/s] model-00002-of-00002.safetensors: 68%|██████▊ | 1.70G/2.51G [00:02<00:00, 847MB/s] model-00002-of-00002.safetensors: 100%|█████████▉| 2.51G/2.51G [00:03<00:00, 695MB/s] Downloading shards: 100%|██████████| 2/2 [00:11<00:00, 5.32s/it] Downloading shards: 100%|██████████| 2/2 [00:11<00:00, 5.63s/it] Traceback (most recent call last): File "/home/user/app/app.py", line 79, in <module> model = Qwen2_5_VLForConditionalGeneration.from_pretrained(model_path, torch_dtype=torch.float16, device_map="cuda") File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 268, in _wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4409, in from_pretrained ) = cls._load_pretrained_model( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4846, in _load_pretrained_model caching_allocator_warmup(model_to_load, expanded_device_map, dtype) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 5852, in caching_allocator_warmup _ = torch.empty(int(param_count), dtype=dtype, device=device, requires_grad=False) File "/usr/local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 319, in _lazy_init torch._C._cuda_init() RuntimeError: No CUDA GPUs are available

Container logs: