runtime error

Exit code: 1. Reason: afetensors: 0%| | 0.00/2.51G [00:00<?, ?B/s] model-00002-of-00002.safetensors: 1%| | 14.2M/2.51G [00:01<04:03, 10.3MB/s] model-00002-of-00002.safetensors: 4%|▎ | 91.0M/2.51G [00:02<00:56, 43.2MB/s] model-00002-of-00002.safetensors: 12%|█▏ | 308M/2.51G [00:03<00:20, 107MB/s]  model-00002-of-00002.safetensors: 20%|█▉ | 493M/2.51G [00:04<00:16, 119MB/s] model-00002-of-00002.safetensors: 27%|██▋ | 672M/2.51G [00:06<00:13, 136MB/s] model-00002-of-00002.safetensors: 47%|████▋ | 1.19G/2.51G [00:07<00:05, 250MB/s] model-00002-of-00002.safetensors: 63%|██████▎ | 1.58G/2.51G [00:08<00:03, 285MB/s] model-00002-of-00002.safetensors: 92%|█████████▏| 2.31G/2.51G [00:09<00:00, 415MB/s] model-00002-of-00002.safetensors: 100%|██████████| 2.51G/2.51G [00:09<00:00, 260MB/s] Traceback (most recent call last): File "/home/user/app/app.py", line 18, in <module> model = AutoModelForImageTextToText.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 571, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 309, in _wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4499, in from_pretrained config = cls._autoset_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2183, in _autoset_attn_implementation cls._check_and_enable_flash_attn_2( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2334, 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: