Tech Report: RLHF Workflow: From Reward Modeling to Online RLHF
Code for Reward Modeling: https://github.com/RLHFlow/RLHF-Reward-Modeling
Code for Online RLHF: https://github.com/RLHFlow/Online-RLHF
RLHFlow
Code for the Workflow of Reinforcement Learning from Human Feedback (RLHF)
- 187 followers
- United States of America
- https://huggingface.co/RLHFlow
- @RLHFlow
- rlhflow.ai@gmail.com
Popular repositories Loading
-
RLHF-Reward-Modeling
RLHF-Reward-Modeling PublicRecipes to train reward model for RLHF.
-
-
Online-DPO-R1
Online-DPO-R1 PublicCodebase for Iterative DPO Using Rule-based Rewards
-
Self-rewarding-reasoning-LLM
Self-rewarding-reasoning-LLM PublicRecipes to train the self-rewarding reasoning LLMs.
-
-
Directional-Preference-Alignment
Directional-Preference-Alignment PublicDirectional Preference Alignment
Repositories
Showing 10 of 10 repositories
- Minimal-RL Public
RLHFlow/Minimal-RL’s past year of commit activity - GVM Public
RLHFlow/GVM’s past year of commit activity - RAFT Public
This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or rejection sampling fine-tuning.
RLHFlow/RAFT’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…