runtime error

Exit code: 1. Reason: sors: 100%|█████████▉| 4.33G/4.33G [00:08<00:00, 500MB/s] Downloading shards: 75%|███████▌ | 3/4 [00:30<00:09, 9.89s/it] model-00004-of-00004.safetensors: 0%| | 0.00/3.73G [00:00<?, ?B/s] model-00004-of-00004.safetensors: 2%|▏ | 73.4M/3.73G [00:01<00:56, 65.0MB/s] model-00004-of-00004.safetensors: 8%|▊ | 294M/3.73G [00:02<00:22, 151MB/s]  model-00004-of-00004.safetensors: 30%|██▉ | 1.10G/3.73G [00:03<00:06, 436MB/s] model-00004-of-00004.safetensors: 42%|████▏ | 1.55G/3.73G [00:04<00:05, 435MB/s] model-00004-of-00004.safetensors: 58%|█████▊ | 2.16G/3.73G [00:05<00:03, 492MB/s] model-00004-of-00004.safetensors: 74%|███████▍ | 2.77G/3.73G [00:06<00:01, 527MB/s] model-00004-of-00004.safetensors: 94%|█████████▍| 3.52G/3.73G [00:07<00:00, 598MB/s] model-00004-of-00004.safetensors: 100%|█████████▉| 3.73G/3.73G [00:07<00:00, 485MB/s] Downloading shards: 100%|██████████| 4/4 [00:38<00:00, 9.12s/it] Downloading shards: 100%|██████████| 4/4 [00:38<00:00, 9.55s/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: