runtime error

Exit code: 1. Reason: PyTorch was not found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. PyTorch was not found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. No model was supplied, defaulted to HuggingFaceTB/SmolLM3-3B and revision a07cc9a. Using a pipeline without specifying a model name and revision in production is not recommended. 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%| | 0.00/1.92k [00:00<?, ?B/s] config.json: 100%|██████████| 1.92k/1.92k [00:00<00:00, 9.12MB/s] Traceback (most recent call last): File "/home/user/app/app.py", line 4, in <module> model = pipeline("text-generation") File "/usr/local/lib/python3.10/site-packages/transformers/pipelines/__init__.py", line 792, in pipeline if isinstance(dtype, str) and hasattr(torch, dtype): NameError: name 'torch' is not defined

Container logs: