WooooDyy/BAPO

Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping" by Zhiheng Xi et al.

33
/ 100
Emerging

This project helps developers fine-tune large language models (LLMs) to perform specific tasks more effectively. It takes an existing LLM and training data, applies a specialized reinforcement learning method, and outputs a more stable and high-performing LLM. Developers working on advanced AI applications would use this to improve their LLMs.

Use this if you are an AI developer looking to stabilize and enhance the performance of large language models through off-policy reinforcement learning, especially for complex generation or reasoning tasks.

Not ideal if you are an end-user simply looking to use an LLM without delving into advanced model training or if you need a solution for models other than LLMs.

LLM fine-tuning Reinforcement learning for AI AI model optimization Natural language generation Advanced AI development
No License No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 5 / 25
Community 9 / 25

How are scores calculated?

Stars

91

Forks

6

Language

Python

License

Last pushed

Jan 29, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/WooooDyy/BAPO"

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