runtime error

Exit code: 1. Reason: 03-of-00003.safetensors: 0%| | 538k/2.60G [00:01<1:47:54, 401kB/s] model-00003-of-00003.safetensors: 3%|▎ | 68.9M/2.60G [00:03<01:54, 22.0MB/s] model-00003-of-00003.safetensors: 5%|▌ | 136M/2.60G [00:04<01:16, 32.2MB/s]  model-00003-of-00003.safetensors: 20%|██ | 521M/2.60G [00:06<00:18, 115MB/s]  model-00003-of-00003.safetensors: 36%|███▌ | 923M/2.60G [00:07<00:08, 189MB/s] model-00003-of-00003.safetensors: 61%|██████▏ | 1.59G/2.60G [00:08<00:03, 318MB/s] model-00003-of-00003.safetensors: 87%|████████▋ | 2.26G/2.60G [00:09<00:00, 374MB/s] model-00003-of-00003.safetensors: 100%|██████████| 2.60G/2.60G [00:10<00:00, 243MB/s] Downloading shards: 100%|██████████| 3/3 [00:52<00:00, 16.23s/it] Downloading shards: 100%|██████████| 3/3 [00:52<00:00, 17.46s/it] Traceback (most recent call last): File "/home/user/app/app.py", line 74, in <module> model = AutoModelForCausalLM.from_pretrained( 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 261, in _wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4159, in from_pretrained config = cls._autoset_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1555, in _autoset_attn_implementation cls._check_and_enable_flash_attn_2( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1699, 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: