Popular repositories Loading

1. OpenCharacterTraining OpenCharacterTraining Public

   Open Character Training

   Jupyter Notebook 77 16

2. PPairS PPairS Public

   [Pair]wise Preference [S]earch with Linear [P]robing: PPairS

   Jupyter Notebook 3

3. LP-as-a-Judge LP-as-a-Judge Public

   experiments on the use of linear classifier heads for llm-as-a-judge tasks.

   Jupyter Notebook 2

4. repeng repeng Public

   Forked from vgel/repeng

   A library for making RepE control vectors

   Jupyter Notebook 1

5. lightbulbmoment22617.github.io lightbulbmoment22617.github.io Public

   HTML

6. OpenRLHF OpenRLHF Public

   Forked from OpenRLHF/OpenRLHF

   An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & RFT & Dynamic Sampling & Async Agent RL)

   Python