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.
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.
Stars
91
Forks
6
Language
Python
License
—
Category
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.
Higher-rated alternatives
agentscope-ai/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement...
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO &...
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
huggingface/alignment-handbook
Robust recipes to align language models with human and AI preferences
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.