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

Pythia v.s. GPT-neox #48

Closed
chuanli11 opened this issue Jan 2, 2023 · 2 comments
Closed

Pythia v.s. GPT-neox #48

chuanli11 opened this issue Jan 2, 2023 · 2 comments

Comments

@chuanli11
Copy link

Hi, thanks for the awesome work.

I notice there are Pythia models and GPT-neox models on Eleuther's HF hub, both seem to be very recent. Wonder what are the the main differences between them, and if there is any preference on one of them.

Thank you.

@haileyschoelkopf
Copy link
Collaborator

Hi,

The Pythia models and GPT-NeoX-20b model were all trained in the same library, and use a very similar architecture.

The Pythia models are primarily intended for research as a consistent set of models. If you’re only looking for performance, then the GPT-J-6B and GPT-NeoX-20b models have been trained on more data and will outperform Pythia models, though the Pythia models should have standard performance for models of their size!

@chuanli11
Copy link
Author

Thank you for the clarification!

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