Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

custom pretrained weights #31

Open
Tinaliu123 opened this issue Apr 6, 2024 · 1 comment
Open

custom pretrained weights #31

Tinaliu123 opened this issue Apr 6, 2024 · 1 comment

Comments

@Tinaliu123
Copy link

Can I load my custom pretrained weights by providing the path to the weights when I load the mode?

@zer0int
Copy link

zer0int commented Apr 10, 2024

I just so happened to implement that yesterday in my fork, for the same reasons (using my fine-tune with it).
You can replace (temporarily rename) the original pre-trained CLIP model in .cache/clip and put your fine-tune of the same model in place of it (though you could also modify the code to use torch.load and just load the pickle / .pt from somewhere else instead):

https://github.com/zer0int/CLIP_Surgery

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants