Popular repositories Loading

1. RLHF-Reward-Modeling RLHF-Reward-Modeling Public

   Recipes to train reward model for RLHF.

   Python 1.2k 88

2. Online-RLHF Online-RLHF Public

   A recipe for online RLHF and online iterative DPO.

   Python 492 47

3. Online-DPO-R1 Online-DPO-R1 Public

   Codebase for Iterative DPO Using Rule-based Rewards

   Python 194 29

4. Self-rewarding-reasoning-LLM Self-rewarding-reasoning-LLM Public

   Recipes to train the self-rewarding reasoning LLMs.

   Python 70 3

5. Directional-Preference-Alignment Directional-Preference-Alignment Public

   Directional Preference Alignment

   56 3

6. RAFT 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.

   Python 25 3