Rank #4,750 1,427 starsPython

MOSS-RLHF

by OpenLMLab (organization)

Secrets of RLHF in Large Language Models Part I: PPO (description from the project’s GitHub page)

Repository facts

Stars: 1,427
Forks: 103
Open issues and pull requests: 39
Primary language: Python
License: Apache License 2.0 (Apache-2.0)
Owner: OpenLMLab · Organization
Created: Jul 5, 2023
Last push: Mar 3, 2024

Topics

Rank #4,750 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Add this badge to your README

Ranked #4,750 in AI on GitHub Shows this repository’s rank in AI on GitHub and links back to this page. Ranks are by stars and change when the list is refreshed. The badge is not an endorsement or a rating. About the badges

Markdown (for a README)

[![Ranked #4,750 in AI on GitHub](https://unitedstatesofamericasuperintelligence.com/badges/github/openlmlab--moss-rlhf.svg)](https://unitedstatesofamericasuperintelligence.com/github/openlmlab--moss-rlhf/)

HTML

<a href="https://unitedstatesofamericasuperintelligence.com/github/openlmlab--moss-rlhf/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/github/openlmlab--moss-rlhf.svg" alt="Ranked #4,750 in AI on GitHub" height="20"></a>

Projects that share this one’s GitHub topics.

Rank 6,260: princeton-nlp/SimPO
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
962 starsPythonMITLast push Feb 16, 2025
Rank 6,648: agentscope-ai/OpenJudge
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
877 starsPythonApache-2.0Last push Sep 11, 2026
Rank 4,338: PKU-Alignment/safe-rlhf
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
1,620 starsPythonApache-2.0Last push Nov 24, 2025
Rank 2,494: cleardusk/3DDFA_V2
The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.
3,154 starsPythonMITLast push Feb 2, 2024
Rank 2,745: readbeyond/aeneas
aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)
2,872 starsPythonAGPL-3.0Last push Jul 25, 2026
Rank 5,652: datadreamer-dev/DataDreamer
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
1,125 starsPythonMITLast push Feb 2, 2025

Repository facts

Topics

Add this badge to your README

Related projects

Rank 6,260: princeton-nlp/SimPO

Rank 6,648: agentscope-ai/OpenJudge

Rank 4,338: PKU-Alignment/safe-rlhf

Rank 2,494: cleardusk/3DDFA_V2

Rank 2,745: readbeyond/aeneas

Rank 5,652: datadreamer-dev/DataDreamer

Support Us