Open yangkaibuaa opened 1 year ago
On HuggingFace, this issue is due to the lack of GPU. If you'd like to run it on HuggingFace, please switch to T4 or A10 device. In Colab notebook, you can also choose T4 or A100 GPU to make it work.
都是程序大佬,能说点小白懂的吗?
我的已遇到这个问题,还是在服务器上运行的那个程序。
Something went wrong 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.
这是什么问题啊?是首选gpu,还是出现这个问题
I have the GPU and cuda 12.1. But the code has such a issue. This issue also happens in Huggingface demo.