runtime error

Exit code: 1. Reason: shards: 75%|███████▌ | 3/4 [00:34<00:11, 11.51s/it] model-00004-of-00004.safetensors: 0%| | 0.00/3.73G [00:00<?, ?B/s] model-00004-of-00004.safetensors: 1%|▏ | 52.4M/3.73G [00:01<01:16, 47.9MB/s] model-00004-of-00004.safetensors: 6%|▌ | 231M/3.73G [00:02<00:28, 121MB/s]  model-00004-of-00004.safetensors: 14%|█▍ | 524M/3.73G [00:03<00:16, 197MB/s] model-00004-of-00004.safetensors: 32%|███▏ | 1.18G/3.73G [00:04<00:06, 371MB/s] model-00004-of-00004.safetensors: 42%|████▏ | 1.56G/3.73G [00:05<00:06, 349MB/s] model-00004-of-00004.safetensors: 56%|█████▌ | 2.09G/3.73G [00:06<00:04, 405MB/s] model-00004-of-00004.safetensors: 68%|██████▊ | 2.54G/3.73G [00:07<00:02, 409MB/s] model-00004-of-00004.safetensors: 82%|████████▏ | 3.04G/3.73G [00:08<00:01, 436MB/s] model-00004-of-00004.safetensors: 100%|█████████▉| 3.73G/3.73G [00:09<00:00, 385MB/s] Downloading shards: 100%|██████████| 4/4 [00:44<00:00, 10.94s/it] Downloading shards: 100%|██████████| 4/4 [00:44<00:00, 11.10s/it] Traceback (most recent call last): File "/home/user/app/app.py", line 19, 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 4097, in from_pretrained model = cls(config, *model_args, **model_kwargs) File "/home/user/.cache/huggingface/modules/transformers_modules/AIDC-AI/Ovis2-8B/d0e09dbe6ce98dc788491976d3c69a539012d44f/modeling_ovis.py", line 293, in __init__ version.parse(importlib.metadata.version("flash_attn")) >= version.parse("2.6.3")), \ AssertionError: Using `flash_attention_2` requires having `flash_attn>=2.6.3` installed.

Container logs: