How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
Paper - Abstract - Updates - Quick Start - Installation - Download the datasets - Create Experiment Script - Single GPU Training (Only for Rho models) - Running the experiments - Code Structure - Initial SFT Checkpoints - Acknowledgement - Citation
The main features of mcgill-nlp/vineppo are: Critic-Free Algorithms, Dense Reward Optimization, RLHF Frameworks.
Projects with overlapping indexed features include: openrlhf/openrlhf — OpenRLHF is a training framework and alignment library designed for reinforcement learning from human feedback across… allenai/finegrainedrlhf — Fine-Grained RLHF. allenai/rl4lms — A modular RL library to fine-tune language models to human preferences. amap-ml/tree-grpo — Tree Search for LLM Agent Reinforcement Learning. anthropics/constitutionalharmlessnesspaper — This repository provides supplementary material for our paper Constitutional AI: Harmlessness from AI Feedback. alibabaresearch/damo-convai — DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.
OpenRLHF is a training framework and alignment library designed for reinforcement learning from human feedback across distributed GPU clusters. It provides tools for aligning large language models and multimodal vision-language models using algorithms such as PPO, GRPO, and DPO. The framework distinguishes itself through a distributed inference engine that overlaps sample rollout with training to increase throughput. It supports scaling to models exceeding 70 billion parameters via parameter sharding and handles long-context sequences through ring-attention sequence parallelism. The project
A modular RL library to fine-tune language models to human preferences
DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.