Closed JeremyChou28 closed 3 months ago
Thanks for the kind words!
Yes it could be because of the torch version. I recommend you create a conda environment and use the specified requirements file and test it.
Thank you for your reply.
In my conda environment, the torch version and other packages meet the requirements.txt.
May I ask what the problem is?
Ah, I'm not sure why in that case. Does the Colab work well for you?
Yes, it works well on Colab.
The current issue is that it appears on my local conda environment, so I would like to ask you the version numbers of various packages that you can run this code in more details.
The torch version you wrote is >=2.0.0, so each version>=2.0.0 is well?
I see. Sure, I'm happy to share them - apologies I'm currently on vacation and will be back soon; but if you need the version numbers immediately, one idea is to check the version numbers used in Colab after the requirements are installed there.
Thank you, I'll try that first. Have a nice vacation.
Hi @JeremyChou28, is this resolved?
Thank you, I have resolved this problem. Maybe the version of python should be python>=3.10
Hi, thank you very much for your work.
May I ask if the following error occurs when loading pre-trained model parameters while running your code? Is it due to the Torch version? My Torch version is 2.2.0.