How is reward calculation done during inference in this model?

#17

by arunasank - opened Nov 25, 2024

Nov 25, 2024

This model seems to be trained using sDPO instead of DPO. How is reward calculation done in this model during inference, for an assistant response to a question?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Your need to confirm your account before you can post a new comment.

· Sign up or log in to comment