runtime error

Exit code: 1. Reason: [00:13<00:00, 371MB/s] Downloading shards: 67%|██████▋ | 2/3 [00:24<00:12, 12.63s/it] model-00003-of-00003.safetensors: 0%| | 0.00/2.60G [00:00<?, ?B/s] model-00003-of-00003.safetensors: 0%| | 538k/2.60G [00:01<1:42:54, 421kB/s] model-00003-of-00003.safetensors: 8%|▊ | 203M/2.60G [00:02<00:24, 99.5MB/s]  model-00003-of-00003.safetensors: 21%|██ | 538M/2.60G [00:03<00:11, 184MB/s]  model-00003-of-00003.safetensors: 39%|███▉ | 1.01G/2.60G [00:04<00:06, 263MB/s] model-00003-of-00003.safetensors: 66%|██████▋ | 1.73G/2.60G [00:05<00:02, 402MB/s] model-00003-of-00003.safetensors: 100%|██████████| 2.60G/2.60G [00:06<00:00, 403MB/s] Downloading shards: 100%|██████████| 3/3 [00:31<00:00, 9.86s/it] Downloading shards: 100%|██████████| 3/3 [00:31<00:00, 10.51s/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: