runtime error

Exit code: 1. Reason: .safetensors: 16%|█▋ | 545M/3.35G [00:02<00:11, 244MB/s]  model-00002-of-00002.safetensors: 36%|███▌ | 1.20G/3.35G [00:03<00:05, 403MB/s] model-00002-of-00002.safetensors: 51%|█████ | 1.70G/3.35G [00:04<00:03, 436MB/s] model-00002-of-00002.safetensors: 69%|██████▉ | 2.31G/3.35G [00:05<00:02, 491MB/s] model-00002-of-00002.safetensors: 85%|████████▍ | 2.84G/3.35G [00:06<00:01, 492MB/s] model-00002-of-00002.safetensors: 100%|█████████▉| 3.35G/3.35G [00:07<00:00, 444MB/s] Downloading shards: 100%|██████████| 2/2 [00:18<00:00, 8.96s/it] Downloading shards: 100%|██████████| 2/2 [00:18<00:00, 9.21s/it] Traceback (most recent call last): File "/home/user/app/app.py", line 10, in <module> "microsoft/Phi-3.5-vision-instruct": AutoModelForCausalLM.from_pretrained("microsoft/Phi-3.5-vision-instruct", trust_remote_code=True, torch_dtype="auto", _attn_implementation="flash_attention_2").cuda().eval() 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 3769, in from_pretrained config = cls._autoset_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1519, in _autoset_attn_implementation cls._check_and_enable_flash_attn_2( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1630, in _check_and_enable_flash_attn_2 raise ImportError(f"{preface} Flash Attention 2 is not available. {install_message}") ImportError: FlashAttention2 has been toggled on, but it cannot be used due to the following error: Flash Attention 2 is not available. Please refer to the documentation of https://huggingface.co/docs/transformers/perf_infer_gpu_one#flashattention-2 to install Flash Attention 2.

Container logs: