runtime error

A new version of the following files was downloaded from https://huggingface.co/visheratin/MC-LLaVA-3b: - modeling_llava.py . Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision. No module named 'flash_attn' No module named 'flash_attn' Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:09<00:09, 9.91s/it] Downloading shards: 100%|██████████| 2/2 [00:13<00:00, 6.37s/it] Downloading shards: 100%|██████████| 2/2 [00:13<00:00, 6.90s/it] Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:05<00:05, 5.05s/it] Loading checkpoint shards: 100%|██████████| 2/2 [00:06<00:00, 2.77s/it] Loading checkpoint shards: 100%|██████████| 2/2 [00:06<00:00, 3.11s/it] No module named 'flash_attn' A new version of the following files was downloaded from https://huggingface.co/visheratin/MC-LLaVA-3b: - processing_llava.py . Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision. Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Traceback (most recent call last): File "/home/user/app/app.py", line 45, in <module> def answer_question(image, question, max_crops, num_tokens, sample, temperature, top_k): File "/usr/local/lib/python3.10/site-packages/spaces/zero/decorator.py", line 113, in _GPU client.startup_report() File "/usr/local/lib/python3.10/site-packages/spaces/zero/client.py", line 45, in startup_report raise RuntimeError("Error while initializing ZeroGPU: Unknown") RuntimeError: Error while initializing ZeroGPU: Unknown

Container logs:

Fetching error logs...