huggingface 下载的Qwen7B-chat/None

[molyswu]

line 317, in set_module_tensor_to_device
new_value = value.to(device)
File "D:\anaconda3\envs\minigpt4qwen\lib\site-packages\torch\cuda_init_.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

pip installed torch-2.1.0+cu118 torchaudio-2.1.0+cu118 torchvision-0.16.0+cu118

[Coobiw]

感谢关注！issue标题里的Qwen7B-chat/None的/None是？然后对于您后续的问题，我感觉应该是cuda版本的问题 你可以试试

import torch
torch.cuda.is_available()

版本库依赖方面可以参考requirements

您这个问题建议参考：https://stackoverflow.com/questions/57814535/assertionerror-torch-not-compiled-with-cuda-enabled-in-spite-upgrading-to-cud