runtime error

Exit code: 1. Reason: vision_encoder.py: 100%|██████████| 10.2k/10.2k [00:00<00:00, 54.2MB/s] model.safetensors: 0%| | 0.00/3.74G [00:00<?, ?B/s] model.safetensors: 1%| | 31.5M/3.74G [00:01<02:45, 22.4MB/s] model.safetensors: 10%|█ | 388M/3.74G [00:02<00:18, 182MB/s]  model.safetensors: 25%|██▌ | 944M/3.74G [00:03<00:08, 334MB/s] model.safetensors: 36%|███▌ | 1.35G/3.74G [00:04<00:06, 362MB/s] model.safetensors: 49%|████▉ | 1.85G/3.74G [00:05<00:04, 406MB/s] model.safetensors: 64%|██████▎ | 2.37G/3.74G [00:06<00:03, 446MB/s] model.safetensors: 77%|███████▋ | 2.88G/3.74G [00:07<00:01, 463MB/s] model.safetensors: 93%|█████████▎| 3.46G/3.74G [00:08<00:00, 501MB/s] model.safetensors: 100%|█████████▉| 3.74G/3.74G [00:09<00:00, 415MB/s] Traceback (most recent call last): File "/home/user/app/app.py", line 16, in <module> moondream = AutoModelForCausalLM.from_pretrained( 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 3804, in from_pretrained config = cls._autoset_attn_implementation( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1534, in _autoset_attn_implementation cls._check_and_enable_flash_attn_2( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1645, 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: