RLHFlow
You can find open-source code, tutorials, and projects related to Reinforcement Learning from Human Feedback (RLHF) here! Code Repositories: https://github.com/RLHFlow/ Models and Datasets: https://huggingface.co/RLHFlow/
Latest Posts
Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts
An interpretable reward modeling approach.
Alignment Guidebook
A guidebook for LLM alignment.
Reward Modeling Part 1: Bradley-Terry Model
This is the recipe for the RLHFlow/RLHF-Reward-Modeling repository used to train the reward model for RLHF.