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

size mismatch for pos_embed: copying a param with shape torch.Size([1, 4096, 2240]) from checkpoint, the shape in current model is torch.Size([1, 1024, 2240]). #112

Open
shaun-ba opened this issue Dec 27, 2024 · 2 comments

Comments

@shaun-ba
Copy link

@city96 Don't suppose this is a simple fix I could patch in? Trying to load the 2k model, I see you have some configs for it so thought it may just work. Not sure where the 4096 is coming from.

@VeteranXT
Copy link

I have similar issue, just for 256 to 1024.

@lawrence-cj
Copy link
Contributor

lawrence-cj commented Jan 2, 2025

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

3 participants