runtime error

Exit code: 1. Reason: � | 2.31G/4.99G [00:12<00:08, 314MB/s] model-00003-of-00004.safetensors: 61%|██████ | 3.05G/4.99G [00:13<00:05, 388MB/s] model-00003-of-00004.safetensors: 91%|█████████ | 4.52G/4.99G [00:14<00:00, 616MB/s] model-00003-of-00004.safetensors: 100%|██████████| 4.99G/4.99G [00:14<00:00, 339MB/s] Downloading shards: 75%|███████▌ | 3/4 [00:41<00:13, 13.85s/it] model-00004-of-00004.safetensors: 0%| | 0.00/1.29G [00:00<?, ?B/s] model-00004-of-00004.safetensors: 1%| | 12.4M/1.29G [00:01<02:06, 10.0MB/s] model-00004-of-00004.safetensors: 6%|▌ | 79.5M/1.29G [00:02<00:35, 34.0MB/s] model-00004-of-00004.safetensors: 48%|████▊ | 616M/1.29G [00:03<00:02, 227MB/s]  model-00004-of-00004.safetensors: 100%|██████████| 1.29G/1.29G [00:04<00:00, 313MB/s] Downloading shards: 100%|██████████| 4/4 [00:45<00:00, 10.01s/it] Downloading shards: 100%|██████████| 4/4 [00:45<00:00, 11.31s/it] Traceback (most recent call last): File "/app/app.py", line 31, in <module> model = AutoModelForCausalLM.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 559, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4091, in from_pretrained config = cls._autoset_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1617, in _autoset_attn_implementation cls._check_and_enable_flash_attn_2( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1756, 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: