runtime error

Exit code: 1. Reason: 1-of-00002.safetensors: 100%|█████████▉| 4.94G/4.94G [00:09<00:00, 533MB/s] model-00002-of-00002.safetensors: 0%| | 0.00/3.35G [00:00<?, ?B/s] model-00002-of-00002.safetensors: 2%|▏ | 62.9M/3.35G [00:01<01:00, 54.6MB/s] model-00002-of-00002.safetensors: 11%|█ | 357M/3.35G [00:02<00:16, 186MB/s]  model-00002-of-00002.safetensors: 32%|███▏ | 1.06G/3.35G [00:03<00:05, 413MB/s] model-00002-of-00002.safetensors: 46%|████▌ | 1.53G/3.35G [00:04<00:04, 435MB/s] model-00002-of-00002.safetensors: 66%|██████▌ | 2.21G/3.35G [00:05<00:02, 522MB/s] model-00002-of-00002.safetensors: 84%|████████▍ | 2.82G/3.35G [00:06<00:00, 552MB/s] model-00002-of-00002.safetensors: 100%|█████████▉| 3.35G/3.35G [00:06<00:00, 490MB/s] Traceback (most recent call last): File "/home/user/app/app.py", line 16, 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 564, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 282, in _wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4404, in from_pretrained config = cls._autoset_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2121, in _autoset_attn_implementation cls._check_and_enable_flash_attn_2( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2272, 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: