Reference implementation for DPO (Direct Preference Optimization)
☆2,920Aug 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.☆19,621Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,124Oct 5, 2026Updated 3 weeks ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆964Feb 16, 2025Updated last year
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆911Sep 30, 2025Updated last year
- Robust recipes to align language models with human and AI preferences☆5,702Sep 23, 2026Updated last month
- 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)☆4,756Jan 8, 2024Updated 2 years ago
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,438May 20, 2026Updated 5 months ago
- Secrets of RLHF in Large Language Models Part I: PPO☆1,428Mar 3, 2024Updated 2 years ago
- Recipes to train reward model for RLHF.☆1,545Apr 24, 2025Updated last year
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,620Nov 24, 2025Updated 11 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆24,024Updated this week
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,154Jun 1, 2023Updated 3 years ago
- A modular RL library to fine-tune language models to human preferences☆2,397Mar 1, 2024Updated 2 years ago
- RewardBench: the first evaluation tool for reward models.☆747Oct 14, 2026Updated 2 weeks ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- AllenAI's post-training codebase☆3,915Updated this week
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆844Jul 1, 2024Updated 2 years ago
- [NIPS2023] RRHF & Wombat☆804Sep 22, 2023Updated 3 years ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,858Jun 17, 2025Updated last year
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,254May 8, 2024Updated 2 years ago
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆21,855Updated this week
- Example models using DeepSpeed☆6,848Sep 30, 2026Updated last month
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,388Jul 25, 2023Updated 3 years ago
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,413Apr 11, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- A framework for few-shot evaluation of language models.☆14,338Sep 14, 2026Updated last month
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆2,021Aug 9, 2025Updated last year
- Ongoing research training transformer models at scale☆18,288Updated this week
- Fast and memory-efficient exact attention☆25,216Updated this week
- Aligning pretrained language models with instruction data generated by themselves.☆4,617Mar 27, 2023Updated 3 years ago
- Official repository for ORPO☆479May 31, 2024Updated 2 years ago
- Official Repo for Open-Reasoner-Zero☆2,100Jun 2, 2025Updated last year
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,774Aug 4, 2024Updated 2 years ago
- Reference implementation for Token-level Direct Preference Optimization(TDPO)☆155Feb 14, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- A recipe for online RLHF and online iterative DPO.☆542Dec 28, 2024Updated last year
- Scalable RL solution for advanced reasoning of language models☆1,873Mar 18, 2025Updated last year
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆398Jan 19, 2025Updated last year
- Simple RL training for reasoning☆3,881Dec 23, 2025Updated 10 months ago
- O1 Replication Journey☆1,997Jan 14, 2025Updated last year
- slime is an LLM training framework for RL Scaling.☆8,752Updated this week
- Scalable toolkit for efficient model alignment☆851Oct 6, 2025Updated last year