runtime error
Exit code: 1. Reason: Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. config.json: 0%| | 0.00/678 [00:00<?, ?B/s][A config.json: 100%|██████████| 678/678 [00:00<00:00, 3.58MB/s] tokenizer_config.json: 0%| | 0.00/63.8k [00:00<?, ?B/s][A tokenizer_config.json: 100%|██████████| 63.8k/63.8k [00:00<00:00, 95.0MB/s] tokenizer.json: 0%| | 0.00/12.9M [00:00<?, ?B/s][A tokenizer.json: 100%|██████████| 12.9M/12.9M [00:00<00:00, 17.4MB/s] special_tokens_map.json: 0%| | 0.00/1.00k [00:00<?, ?B/s][A special_tokens_map.json: 100%|██████████| 1.00k/1.00k [00:00<00:00, 4.45MB/s] chat_template.jinja: 0%| | 0.00/16.8k [00:00<?, ?B/s][A chat_template.jinja: 100%|██████████| 16.8k/16.8k [00:00<00:00, 40.6MB/s] Traceback (most recent call last): File "/app/app.py", line 33, in <module> raise RuntimeError( ...<2 lines>... ) RuntimeError: LOAD_IN_4BIT=true requires a CUDA GPU Space. Please switch the Space hardware to T4/L4 or set LOAD_IN_4BIT=false.
Container logs:
Fetching error logs...