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

Preliminary implementation of PIE model #96

Merged
merged 9 commits into from
Dec 16, 2024
Merged

Preliminary implementation of PIE model #96

merged 9 commits into from
Dec 16, 2024

Conversation

matsen
Copy link
Contributor

@matsen matsen commented Dec 12, 2024

Preliminary implementation of DASM model which uses a protein embedding as input, which hilariously back-translates our AA indexing into a string and passes it to ESM for pre-embedding. Slow!

@matsen matsen linked an issue Dec 12, 2024 that may be closed by this pull request
@matsen matsen self-assigned this Dec 12, 2024
@matsen matsen requested a review from willdumm December 13, 2024 16:01
@matsen matsen marked this pull request as ready for review December 13, 2024 16:01
Copy link
Contributor

@willdumm willdumm left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I haven't tried it out yet, but looks good!

@matsen matsen changed the title Train models using ESM embedding as input Preliminary implementation of PIE model Dec 16, 2024
@matsen matsen merged commit 9c78482 into main Dec 16, 2024
2 checks passed
@matsen matsen deleted the 95-esm branch December 16, 2024 11:11
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.

train DXSMs using ESM2 embeddings as input
2 participants