runtime error

Exit code: 1. Reason: 02-of-00002.safetensors: 13%|█▎ | 430M/3.35G [00:02<00:13, 224MB/s]  model-00002-of-00002.safetensors: 28%|██▊ | 944M/3.35G [00:03<00:06, 351MB/s] model-00002-of-00002.safetensors: 45%|████▍ | 1.50G/3.35G [00:04<00:04, 428MB/s] model-00002-of-00002.safetensors: 59%|█████▉ | 1.97G/3.35G [00:05<00:03, 439MB/s] model-00002-of-00002.safetensors: 74%|███████▍ | 2.49G/3.35G [00:06<00:01, 464MB/s] model-00002-of-00002.safetensors: 100%|█████████▉| 3.35G/3.35G [00:07<00:00, 588MB/s] model-00002-of-00002.safetensors: 100%|█████████▉| 3.35G/3.35G [00:07<00:00, 452MB/s] Downloading shards: 100%|██████████| 2/2 [00:18<00:00, 9.17s/it] Downloading shards: 100%|██████████| 2/2 [00:18<00:00, 9.49s/it] Traceback (most recent call last): File "/home/user/app/app.py", line 17, in <module> model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cuda", trust_remote_code=True, torch_dtype="auto") File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 559, in from_pretrained return model_class.from_pretrained( 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 4266, in from_pretrained config = cls._autoset_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1626, in _autoset_attn_implementation cls._check_and_enable_flash_attn_2( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1773, in _check_and_enable_flash_attn_2 raise ValueError( ValueError: FlashAttention2 has been toggled on, but it cannot be used due to the following error: Flash Attention 2 is not available on CPU. Please make sure torch can access a CUDA device.

Container logs: