runtime error

al tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Traceback (most recent call last): File "/home/user/app/app.py", line 10, in <module> run_local(model_path, backend_config=backend_config, server_name="huggingface-space") File "/usr/local/lib/python3.10/site-packages/lmdeploy/serve/gradio/turbomind_coupled.py", line 160, in run_local InterFace.async_engine = AsyncEngine( File "/usr/local/lib/python3.10/site-packages/lmdeploy/serve/async_engine.py", line 189, in __init__ self._build_turbomind(model_path=model_path, File "/usr/local/lib/python3.10/site-packages/lmdeploy/serve/async_engine.py", line 234, in _build_turbomind self.engine = tm.TurboMind.from_pretrained( File "/usr/local/lib/python3.10/site-packages/lmdeploy/turbomind/turbomind.py", line 342, in from_pretrained return cls(model_path=pretrained_model_name_or_path, File "/usr/local/lib/python3.10/site-packages/lmdeploy/turbomind/turbomind.py", line 144, in __init__ self.model_comm = self._from_hf(model_source=model_source, File "/usr/local/lib/python3.10/site-packages/lmdeploy/turbomind/turbomind.py", line 232, in _from_hf output_model_name, cfg = get_output_model_registered_name_and_config( File "/usr/local/lib/python3.10/site-packages/lmdeploy/turbomind/deploy/converter.py", line 158, in get_output_model_registered_name_and_config if not torch.cuda.is_bf16_supported(): File "/usr/local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 157, in is_bf16_supported torch.cuda.get_device_properties(torch.cuda.current_device()).major >= 8 File "/usr/local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 787, in current_device _lazy_init() File "/usr/local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 302, in _lazy_init torch._C._cuda_init() RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx

Container logs: