Skip to content

Swap to using nn.Embedding #103

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

Merged
merged 12 commits into from
Apr 19, 2025
Merged

Swap to using nn.Embedding #103

merged 12 commits into from
Apr 19, 2025

Conversation

CompRhys
Copy link
Owner

@CompRhys CompRhys commented Apr 12, 2025

This should lead to a slight speed up and also reduces the size of the cache of the datasets dramatically. This cache reduction is needed to be able to scale to larger datasets.

todo:

  • Work out what to do with wrenformer. Probably splitting wrenformer and roostformer into two models is the best way.

@CompRhys CompRhys merged commit 6c72299 into main Apr 19, 2025
8 checks passed
@CompRhys CompRhys deleted the nn-embeddings branch April 19, 2025 20:55
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

Successfully merging this pull request may close these issues.

1 participant