runtime error

Exit code: 1. Reason: ██████████| 1.37k/1.37k [00:00<00:00, 11.1MB/s] vocab.txt: 0%| | 0.00/599 [00:00<?, ?B/s] vocab.txt: 100%|██████████| 599/599 [00:00<00:00, 3.24MB/s] Loading models... Traceback (most recent call last): File "/app/app.py", line 21, in <module> model_list = nar.load_model(device, "CapTTS") File "/app/capspeech/nar/generate.py", line 191, in load_model checkpoint = torch.load(model_path)['model'] ~~~~~~~~~~^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/torch/serialization.py", line 1540, in load return _load( opened_zipfile, ...<3 lines>... **pickle_load_args, ) File "/usr/local/lib/python3.13/site-packages/torch/serialization.py", line 2143, in _load result = unpickler.load() File "/usr/local/lib/python3.13/site-packages/torch/_weights_only_unpickler.py", line 539, in load self.append(self.persistent_load(pid)) ~~~~~~~~~~~~~~~~~~~~^^^^^ File "/usr/local/lib/python3.13/site-packages/torch/serialization.py", line 2107, in persistent_load typed_storage = load_tensor( dtype, nbytes, key, _maybe_decode_ascii(location) ) File "/usr/local/lib/python3.13/site-packages/torch/serialization.py", line 2073, in load_tensor wrap_storage = restore_location(storage, location) File "/usr/local/lib/python3.13/site-packages/torch/serialization.py", line 707, in default_restore_location result = fn(storage, location) File "/usr/local/lib/python3.13/site-packages/torch/serialization.py", line 640, in _deserialize device = _validate_device(location, backend_name) File "/usr/local/lib/python3.13/site-packages/torch/serialization.py", line 609, in _validate_device raise RuntimeError( ...<5 lines>... ) RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

Container logs: