Reference implementation for DPO (Direct Preference Optimization)
☆2,896Aug 11, 2024Updated last year
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.☆18,898Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,831Jul 14, 2026Updated last week
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆956Feb 16, 2025Updated last year
- Robust recipes to align language models with human and AI preferences☆5,639May 26, 2026Updated last month
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆908Sep 30, 2025Updated 9 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,753Jan 8, 2024Updated 2 years ago
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,416May 20, 2026Updated 2 months ago
- Secrets of RLHF in Large Language Models Part I: PPO☆1,427Mar 3, 2024Updated 2 years ago
- Recipes to train reward model for RLHF.☆1,534Apr 24, 2025Updated last year
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,611Nov 24, 2025Updated 7 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,587Updated this week
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,150Jun 1, 2023Updated 3 years ago
- RewardBench: the first evaluation tool for reward models.☆727Feb 16, 2026Updated 5 months ago
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆845Jul 1, 2024Updated 2 years 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 modular RL library to fine-tune language models to human preferences☆2,393Mar 1, 2024Updated 2 years ago
- [NIPS2023] RRHF & Wombat☆806Sep 22, 2023Updated 2 years ago
- AllenAI's post-training codebase☆3,803Updated this week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆21,426Updated this week
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,247May 8, 2024Updated 2 years ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,851Jun 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☆6,831Updated this week
- A framework for few-shot evaluation of language models.☆13,359Jul 13, 2026Updated last week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆2,006Aug 9, 2025Updated 11 months ago
- Fast and memory-efficient exact attention☆24,502Updated this week
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,776Aug 4, 2024Updated last year
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,393Jul 25, 2023Updated 2 years ago
- Ongoing research training transformer models at scale☆17,140Updated this week
- Aligning pretrained language models with instruction data generated by themselves.☆4,606Mar 27, 2023Updated 3 years ago
- Official Repo for Open-Reasoner-Zero☆2,096Jun 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"☆398Jan 19, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Official repository for ORPO☆480May 31, 2024Updated 2 years ago
- O1 Replication Journey☆2,000Jan 14, 2025Updated last year
- Simple RL training for reasoning☆3,868Dec 23, 2025Updated 6 months ago
- Scalable toolkit for efficient model alignment☆850Oct 6, 2025Updated 9 months ago
- slime is an LLM post-training framework for RL Scaling.☆7,569Updated this week
- Scalable RL solution for advanced reasoning of language models☆1,865Mar 18, 2025Updated last year
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆73,422Updated this week