runtime error

Exit code: 1. Reason: p install' wheel command for your CUDA / PyTorch versions, share `torch.__version__` and `nvidia-smi` output (if available). Traceback (most recent call last): File "/app/app.py", line 88, in <module> model = AutoModelForCausalLM.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 597, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 277, in _wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4971, in from_pretrained model = cls(config, *model_args, **model_kwargs) File "/root/.cache/huggingface/modules/transformers_modules/microsoft/Phi_hyphen_4_hyphen_multimodal_hyphen_instruct/33e62acdd07cd7d6635badd529aa0a3467bb9c6a/modeling_phi4mm.py", line 1941, in __init__ super().__init__(config) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2076, in __init__ self.config._attn_implementation_internal = self._check_and_adjust_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2686, in _check_and_adjust_attn_implementation applicable_attn_implementation = self.get_correct_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2714, in get_correct_attn_implementation self._flash_attn_2_can_dispatch(is_init_check) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2422, in _flash_attn_2_can_dispatch raise ImportError(f"{preface} the package flash_attn seems to be not installed. {install_message}") ImportError: FlashAttention2 has been toggled on, but it cannot be used due to the following error: the package flash_attn seems to be not installed. Please refer to the documentation of https://huggingface.co/docs/transformers/perf_infer_gpu_one#flashattention-2 to install Flash Attention 2.

Container logs: