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.

Sign up for GitHub

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

Jump to bottom

Weights upcasted to float32 at load time #23

Closed
mfuntowicz opened this issue Apr 10, 2024 · 2 comments
Closed

Weights upcasted to float32 at load time #23

mfuntowicz opened this issue Apr 10, 2024 · 2 comments
Assignees
@tengomucho
Labels
enhancement New feature or request

Comments

@mfuntowicz
Copy link
Member

When loading Gemma model(s) the weights are upcasted towards float32 representation increasing the memory requirements by twice and slowing down computations
@mfuntowicz mfuntowicz added the enhancement New feature or request label Apr 10, 2024
@tengomucho
Copy link
Collaborator

This is being fixed in #21, you can see the change here: cd99226

@tengomucho
Copy link
Collaborator

Fixed in a different way, anyway it's in #21.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@tengomucho tengomucho

Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@mfuntowicz @tengomucho