runtime error

98%|█████████▊| 5.26G/5.38G [01:38<00:02, 47.7MB/s] 98%|█████████▊| 5.27G/5.38G [01:38<00:01, 57.6MB/s] 98%|█████████▊| 5.28G/5.38G [01:39<00:01, 53.8MB/s] 98%|█████████▊| 5.29G/5.38G [01:39<00:01, 49.5MB/s] 98%|█████████▊| 5.30G/5.38G [01:39<00:01, 50.7MB/s] 99%|█████████▊| 5.30G/5.38G [01:39<00:01, 47.5MB/s] 99%|█████████▊| 5.31G/5.38G [01:39<00:01, 47.1MB/s] 99%|█████████▉| 5.32G/5.38G [01:39<00:01, 47.8MB/s] 99%|█████████▉| 5.33G/5.38G [01:40<00:00, 63.6MB/s] 99%|█████████▉| 5.34G/5.38G [01:40<00:00, 42.9MB/s] 99%|█████████▉| 5.35G/5.38G [01:40<00:00, 44.2MB/s] 100%|█████████▉| 5.35G/5.38G [01:40<00:00, 43.5MB/s] 100%|█████████▉| 5.36G/5.38G [01:40<00:00, 51.5MB/s] 100%|█████████▉| 5.37G/5.38G [01:41<00:00, 49.5MB/s] 100%|█████████▉| 5.38G/5.38G [01:41<00:00, 54.7MB/s] 100%|██████████| 5.38G/5.38G [01:41<00:00, 57.1MB/s] Traceback (most recent call last): File "/home/user/app/app.py", line 52, in <module> model = model.cuda() File "/home/user/.local/lib/python3.10/site-packages/lightning_fabric/utilities/device_dtype_mixin.py", line 69, in cuda device = torch.device("cuda", torch.cuda.current_device()) File "/home/user/.local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 674, in current_device _lazy_init() File "/home/user/.local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 247, in _lazy_init torch._C._cuda_init() File "/home/user/.local/lib/python3.10/site-packages/spaces/gpu/torch.py", line 60, in _cuda_init_raise raise RuntimeError( RuntimeError: CUDA must not be initialized in the main process on Spaces with Stateless GPU environment. You can look at this Stacktrace to find out which part of your code triggered a CUDA init

Container logs: