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

Regarding training data of EAGLE #128

Open

KanghoonYoon opened this issue Sep 4, 2024 · 1 comment

KanghoonYoon commented Sep 4, 2024

I want to clarify the portion of training dataset, ShareGPT.

The current code uses the 100 samples as training dataset for EAGLE.

But in the paper, EAGLES is trained with 68,000 samples.

What should I follow to reproduce EAGLES from scratch ? :)

Collaborator

Liyuhui-12 commented Sep 11, 2024

The default value of 100 is for debugging purposes; you can specify this parameter during training.

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