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

Fine-tuning llama-70b? #62

Open

JH-ninjatech opened this issue Feb 17, 2025 · 2 comments

JH-ninjatech commented Feb 17, 2025

Hi @Muennighoff

I am wondering if I can use s1 data to finetune llama-70B model. Have your team tried on 70B before?

Contributor

Muennighoff commented Feb 17, 2025

We havn't tried 70B but I'm sure it should work! Btw I recommend using our latest data 1.1: https://hf.co/datasets/simplescaling/s1K-1.1

Author

JH-ninjatech commented Feb 17, 2025

Hi @Muennighoff if I want to finetune the 70B, is 16 H100 enough if I keep the max_seq_len to 32768

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