Reference implementation for DPO (Direct Preference Optimization)
☆2,907Aug 11, 2024Updated 2 years ago
Alternatives and similar repositories for direct-preference-optimization
Users that are interested in direct-preference-optimization are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Train transformer language models with reinforcement learning.☆19,180Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,960Aug 13, 2026Updated 2 weeks ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆958Feb 16, 2025Updated last year
- Robust recipes to align language models with human and AI preferences☆5,672May 26, 2026Updated 3 months ago
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆910Sep 30, 2025Updated 11 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,755Jan 8, 2024Updated 2 years ago
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,422May 20, 2026Updated 3 months ago
- Secrets of RLHF in Large Language Models Part I: PPO☆1,430Mar 3, 2024Updated 2 years ago
- Recipes to train reward model for RLHF.☆1,541Apr 24, 2025Updated last year
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,613Nov 24, 2025Updated 9 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,204Updated this week
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,149Jun 1, 2023Updated 3 years ago
- RewardBench: the first evaluation tool for reward models.☆733Feb 16, 2026Updated 6 months ago
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆845Jul 1, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- A modular RL library to fine-tune language models to human preferences☆2,394Mar 1, 2024Updated 2 years ago
- [NIPS2023] RRHF & Wombat☆804Sep 22, 2023Updated 2 years ago
- AllenAI's post-training codebase☆3,854Updated this week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆21,608Updated this week
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,255May 8, 2024Updated 2 years ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,856Jun 17, 2025Updated last year
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,411Apr 11, 2024Updated 2 years ago
- Example models using DeepSpeed☆6,841Updated this week
- A framework for few-shot evaluation of language models.☆13,831Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆2,013Aug 9, 2025Updated last year
- Fast and memory-efficient exact attention☆24,805Updated this week
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,776Aug 4, 2024Updated 2 years ago
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,391Jul 25, 2023Updated 3 years ago
- Ongoing research training transformer models at scale☆17,674Updated this week
- Aligning pretrained language models with instruction data generated by themselves.☆4,609Mar 27, 2023Updated 3 years ago
- Official Repo for Open-Reasoner-Zero☆2,100Jun 2, 2025Updated last year
- A recipe for online RLHF and online iterative DPO.☆544Dec 28, 2024Updated last year
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆397Jan 19, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Official repository for ORPO☆479May 31, 2024Updated 2 years ago
- O1 Replication Journey☆2,002Jan 14, 2025Updated last year
- slime is an LLM post-training framework for RL Scaling.☆8,313Updated this week
- Simple RL training for reasoning☆3,874Dec 23, 2025Updated 8 months ago
- Scalable toolkit for efficient model alignment☆852Oct 6, 2025Updated 10 months ago
- Scalable RL solution for advanced reasoning of language models☆1,872Mar 18, 2025Updated last year
- A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.☆6,899Dec 17, 2025Updated 8 months ago