What prompts are used in RLAIF?

#13

by chujiezheng - opened Apr 6

Apr 6

Thanks for your great work. Could you disclose what prompts are used in the policy sampling steps in RLAIF?

Nexusflow org Apr 8

Thank you for your question! It's using the same prompt from the Nectar dataset here: https://huggingface.co/datasets/berkeley-nest/Nectar

banghua changed discussion status to closed Apr 8

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

Tap or paste here to upload images

· Sign up or log in to comment