runtime error

Exit code: 1. Reason: ▏| 3.06G/3.32G [00:14<00:01, 256MB/s] model-00002-of-00002.safetensors: 100%|██████████| 3.32G/3.32G [00:15<00:00, 220MB/s] Downloading shards: 100%|██████████| 2/2 [00:32<00:00, 16.02s/it] Downloading shards: 100%|██████████| 2/2 [00:32<00:00, 16.21s/it] Traceback (most recent call last): File "/home/user/app/app.py", line 14, in <module> model = AutoModelForCausalLM.from_pretrained(model_name, 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 3832, in from_pretrained model = cls(config, *model_args, **model_kwargs) File "/home/user/.cache/huggingface/modules/transformers_modules/AIDC-AI/Ovis1.6-Llama3.2-3B/b8d93d7468f47fd803eb26ec2c1bc2d7e5fba60e/modeling_ovis.py", line 280, in __init__ self.llm = AutoModelForCausalLM.from_config(self.config.llm_config, **attn_kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 438, in from_config return model_class._from_config(config, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1486, in _from_config config = cls._autoset_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1556, in _autoset_attn_implementation cls._check_and_enable_flash_attn_2( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1667, 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: