Sphere-AI-Lab/orbit

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).

Implementing a tiny RL framework from scratch with as little dependencies as possible, can run RL on real LLMS using PC/laptops with limited resources.

Scalable toolkit for efficient model reinforcement

Democratizing Reinforcement Learning for LLMs

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.