runtime error

ice] To update, run: /usr/local/bin/python -m pip install --upgrade pip Downloading shards: 0%| | 0/4 [00:00<?, ?it/s] Downloading shards: 25%|██▌ | 1/4 [00:17<00:51, 17.11s/it] Downloading shards: 50%|█████ | 2/4 [00:24<00:22, 11.43s/it] Downloading shards: 75%|███████▌ | 3/4 [00:40<00:13, 13.59s/it] Downloading shards: 100%|██████████| 4/4 [00:47<00:00, 10.82s/it] Downloading shards: 100%|██████████| 4/4 [00:47<00:00, 11.83s/it] The model was loaded with use_flash_attention_2=True, which is deprecated and may be removed in a future release. Please use `attn_implementation="flash_attention_2"` instead. You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. You are attempting to use Flash Attention 2.0 without specifying a torch dtype. This might lead to unexpected behaviour Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s] Loading checkpoint shards: 25%|██▌ | 1/4 [00:10<00:30, 10.17s/it] Loading checkpoint shards: 50%|█████ | 2/4 [00:13<00:12, 6.12s/it] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:15<00:04, 4.27s/it] Loading checkpoint shards: 100%|██████████| 4/4 [00:16<00:00, 4.08s/it] Traceback (most recent call last): File "/home/user/app/app.py", line 4, in <module> from chatbot import model_inference, EXAMPLES, chatbot File "/home/user/app/chatbot.py", line 216, in <module> def model_inference( user_prompt, chat_history): File "/usr/local/lib/python3.10/site-packages/spaces/zero/decorator.py", line 107, 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: