WangJingyao07/Awesome-GRPO

Codebase of GRPO: Implementations and Resources of GRPO and Its Variants

39
/ 100
Emerging

This repository provides a collection of code implementations and research papers for GRPO and its variations, which are advanced techniques for fine-tuning large language models (LLMs) using reinforcement learning. It helps AI researchers and practitioners improve LLM performance by offering a centralized hub for different optimization strategies. You input an LLM and training data, and the output is a more finely tuned, capable LLM.

276 stars.

Use this if you are an AI researcher or machine learning engineer looking to experiment with and apply advanced reinforcement learning techniques (specifically GRPO and its variants) to fine-tune large language models for better performance.

Not ideal if you are looking for a simple, out-of-the-box solution for general LLM usage without delving into advanced fine-tuning methodologies or if you are not familiar with reinforcement learning concepts for LLMs.

LLM fine-tuning Reinforcement Learning Natural Language Processing Deep Learning AI research
No License No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 7 / 25
Community 16 / 25

How are scores calculated?

Stars

276

Forks

31

Language

Python

License

Last pushed

Dec 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/WangJingyao07/Awesome-GRPO"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.