anthropics / hh-rlhfView external linksLinks
Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"
☆1,814Jun 17, 2025Updated 7 months ago
Alternatives and similar repositories for hh-rlhf
Users that are interested in hh-rlhf are comparing it to the libraries listed below
Sorting:
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,742Jan 8, 2024Updated 2 years ago
- A modular RL library to fine-tune language models to human preferences☆2,377Mar 1, 2024Updated last year
- ☆250Dec 21, 2022Updated 3 years ago
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,582Nov 24, 2025Updated 2 months ago
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,377Jul 25, 2023Updated 2 years ago
- Train transformer language models with reinforcement learning.☆17,360Updated this week
- [NIPS2023] RRHF & Wombat☆808Sep 22, 2023Updated 2 years ago
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,092Jun 1, 2023Updated 2 years ago
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆842Jul 1, 2024Updated last year
- Aligning pretrained language models with instruction data generated by themselves.☆4,573Mar 27, 2023Updated 2 years ago
- Code for "Learning to summarize from human feedback"☆1,059Sep 5, 2023Updated 2 years ago
- Instruction Tuning with GPT-4☆4,340Jun 11, 2023Updated 2 years ago
- ☆1,559Feb 5, 2026Updated last week
- A framework for few-shot evaluation of language models.☆11,393Updated this week
- Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Langu…☆354Jun 18, 2023Updated 2 years ago
- RewardBench: the first evaluation tool for reward models.☆687Jan 31, 2026Updated 2 weeks ago
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,289Dec 9, 2025Updated 2 months ago
- Robust recipes to align language models with human and AI preferences☆5,495Sep 8, 2025Updated 5 months ago
- Expanding natural instructions☆1,030Dec 11, 2023Updated 2 years ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,433Mar 20, 2024Updated last year
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,768Aug 4, 2024Updated last year
- ☆329Jul 2, 2024Updated last year
- Reference implementation for DPO (Direct Preference Optimization)☆2,850Aug 11, 2024Updated last year
- Scalable toolkit for efficient model alignment☆852Oct 6, 2025Updated 4 months ago
- Secrets of RLHF in Large Language Models Part I: PPO☆1,416Mar 3, 2024Updated last year
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,946Aug 9, 2025Updated 6 months ago
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,731Nov 15, 2025Updated 3 months ago
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆30,266Jul 17, 2024Updated last year
- Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM☆7,882Oct 11, 2025Updated 4 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆8,989Feb 6, 2026Updated last week
- ☆1,257Dec 11, 2022Updated 3 years ago
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆20,619Updated this week
- Dromedary: towards helpful, ethical and reliable LLMs.☆1,143Sep 18, 2025Updated 4 months ago
- Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models☆3,199Jul 19, 2024Updated last year
- AllenAI's post-training codebase☆3,573Updated this week
- LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath☆9,477Jun 7, 2025Updated 8 months ago
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆39,402Jun 2, 2025Updated 8 months ago
- Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)☆2,783Mar 13, 2024Updated last year
- Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models …☆2,667Updated this week