kvfrans/lmpo

Scalable toolkit for efficient model reinforcement

Comprehensive toolkit for Reinforcement Learning from Human Feedback (RLHF) training, featuring instruction fine-tuning, reward model training, and support for PPO and DPO algorithms with various configurations for the Transformer 5 models including Qwen 3.0

Democratizing Reinforcement Learning for LLMs

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

A Lightweight LLM Post-Training Library

Code For All-Quadrant Bounded Clipping GRPO. arxiv.org/pdf/2601.03895

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

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM