runtime error

Exit code: 1. Reason: model-00002-of-00003.safetensors: 95%|█████████▍| 4.67G/4.93G [00:13<00:00, 806MB/s] model-00002-of-00003.safetensors: 100%|██████████| 4.93G/4.93G [00:13<00:00, 359MB/s] Downloading shards: 67%|██████▋ | 2/3 [00:27<00:13, 13.57s/it] model-00003-of-00003.safetensors: 0%| | 0.00/2.60G [00:00<?, ?B/s] model-00003-of-00003.safetensors: 3%|▎ | 67.1M/2.60G [00:04<02:47, 15.1MB/s] model-00003-of-00003.safetensors: 23%|██▎ | 587M/2.60G [00:05<00:15, 133MB/s]  model-00003-of-00003.safetensors: 87%|████████▋ | 2.26G/2.60G [00:06<00:00, 521MB/s] model-00003-of-00003.safetensors: 100%|██████████| 2.60G/2.60G [00:07<00:00, 350MB/s] Downloading shards: 100%|██████████| 3/3 [00:34<00:00, 10.77s/it] Downloading shards: 100%|██████████| 3/3 [00:34<00:00, 11.49s/it] Traceback (most recent call last): File "/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: