model.generate.scores returning two scores

allenai / RL4LMs

A modular RL library to fine-tune language models to human preferences

https://rl4lms.apps.allenai.org/

Apache License 2.0

2.13k stars 191 forks source link

Open debjitpaul opened 1 year ago

debjitpaul commented 1 year ago

Dear contributors,

Thank you so much! This repo is excellent!

What is the difference between raw_logits, and processed_logits?

How does it differ from the normal hugging face model.generate.score?

Thank you, Debjit