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

LAFF transformer #4

Merged
merged 6 commits into from
Nov 26, 2024
Merged

LAFF transformer #4

merged 6 commits into from
Nov 26, 2024

Conversation

seanmacavaney
Copy link
Collaborator

@Mandeep-Rathee can you take a look to make sure this implementation looks right? It's based off the code here and here.

I've also packaged up laff into a huggingface model at macavaney/laff that allows it (and its tokenizer) to be loaded with from_pretrained, avoiding the stuff with hf_hub_download. Feel free to merge it into mandeep-rathee/laff-model if you like and I'll drop mine.

The next step will be writing a method to apply to a corpus graph.

@Mandeep-Rathee
Copy link

All looks good. We just need to add to update requirement.txt with transformers.

thanks

@seanmacavaney
Copy link
Collaborator Author

Thanks! It's set as an optional dependency, since the transformers package is pretty hefty and not necessary unless you're using the LAFF model.

@seanmacavaney seanmacavaney merged commit 781891f into main Nov 26, 2024
4 checks passed
@seanmacavaney seanmacavaney deleted the laff_model branch November 26, 2024 09:27
@Mandeep-Rathee
Copy link

that's true. Great!! thanks a lot, @seanmacavaney

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.

2 participants