runtime error

ator (setup.py): started Building wheel for transformers_stream_generator (setup.py): finished with status 'done' Created wheel for transformers_stream_generator: filename=transformers_stream_generator-0.0.4-py3-none-any.whl size=12315 sha256=f36a237b54ba66c906dd48c5ed71df57b342d559729039b2db7452df4436720d Stored in directory: /home/user/.cache/pip/wheels/6a/ff/7b/74774d96fbe8269743a0e334d378071810aa0aea1cda75fb83 Successfully built transformers_stream_generator Installing collected packages: safetensors, huggingface-hub, tokenizers, transformers, transformers_stream_generator Attempting uninstall: huggingface-hub Found existing installation: huggingface-hub 0.18.0 Uninstalling huggingface-hub-0.18.0: Successfully uninstalled huggingface-hub-0.18.0 Successfully installed huggingface-hub-0.17.3 safetensors-0.4.0 tokenizers-0.14.1 transformers-4.34.1 transformers_stream_generator-0.0.4 [notice] A new release of pip available: 22.3.1 -> 23.3 [notice] To update, run: python -m pip install --upgrade pip None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. Traceback (most recent call last): File "/home/user/app/app.py", line 10, in <module> model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True).float() #.half().to("cuda") File "/home/user/.local/lib/python3.10/site-packages/transformers/utils/import_utils.py", line 1222, in __getattribute__ requires_backends(cls, cls._backends) File "/home/user/.local/lib/python3.10/site-packages/transformers/utils/import_utils.py", line 1210, in requires_backends raise ImportError("".join(failed)) ImportError: AutoModelForCausalLM requires the PyTorch library but it was not found in your environment. Checkout the instructions on the installation page: https://pytorch.org/get-started/locally/ and follow the ones that match your environment. Please note that you may need to restart your runtime after installation.

Container logs: