other8.0 / 10
RLHF and RLAIF in GPT-NeoX
Abstract
Implementation of Reinforcement Learning from Human Feedback and AI Feedback in GPT-NeoX
Research area
RLHF
Published
—
Source
other
Org
EleutherAI
Sign in to read and join the discussion.
Implementation of Reinforcement Learning from Human Feedback and AI Feedback in GPT-NeoX