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

Implementation details about SFT data #7

Open
Chen-GX opened this issue Nov 22, 2024 · 1 comment
Open

Implementation details about SFT data #7

Chen-GX opened this issue Nov 22, 2024 · 1 comment

Comments

@Chen-GX
Copy link

Chen-GX commented Nov 22, 2024

Thank you for your impressive work ! 🥳

I am interested in extending similar capabilities to other models and would you like to provide the SFT data?
I have found your rationale in this link. I am not sure whether I can fine-tune other model based on these rationales.

Thanks.

@weizhepei
Copy link
Owner

@Chen-GX Hi Guoxin, many thanks for your interest in our work!

Yes, the provided rationale data can be directly used to fine-tune other models. Note that our method does not require any external supervision to generate such rationales, so you can also generate rationales on your own corpus with any model using our script generate_rationale.sh.

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

2 participants