rlhf

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models

RewardBench: the first evaluation tool for reward models.

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

🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

The official implementation of Self-Play Preference Optimization (SPPO)

Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)

A recipe for online RLHF and online iterative DPO.

A curated collection of papers and resources on On-Policy Distillation for Large Language Models.

[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.