Reference implementation for DPO (Direct Preference Optimization)
☆2,855Aug 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
Sorting:
- Train transformer language models with reinforcement learning.☆17,460Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆9,037Feb 21, 2026Updated last week
- Robust recipes to align language models with human and AI preferences☆5,506Sep 8, 2025Updated 5 months ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆946Feb 16, 2025Updated last year
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,741Jan 8, 2024Updated 2 years ago
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆904Sep 30, 2025Updated 5 months ago
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,301Dec 9, 2025Updated 2 months ago
- Secrets of RLHF in Large Language Models Part I: PPO☆1,416Mar 3, 2024Updated last year
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,091Jun 1, 2023Updated 2 years ago
- Recipes to train reward model for RLHF.☆1,515Apr 24, 2025Updated 10 months ago
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,585Nov 24, 2025Updated 3 months ago
- RewardBench: the first evaluation tool for reward models.☆696Feb 16, 2026Updated last week
- verl: Volcano Engine Reinforcement Learning for LLMs☆19,339Updated this week
- A modular RL library to fine-tune language models to human preferences☆2,378Mar 1, 2024Updated last year
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆842Jul 1, 2024Updated last year
- [NIPS2023] RRHF & Wombat☆809Sep 22, 2023Updated 2 years ago
- AllenAI's post-training codebase☆3,592Updated this week
- A framework for few-shot evaluation of language models.☆11,478Feb 15, 2026Updated last week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆20,678Updated this week
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,235May 8, 2024Updated last year
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,816Jun 17, 2025Updated 8 months ago
- Example models using DeepSpeed☆6,785Feb 7, 2026Updated 3 weeks ago
- Fast and memory-efficient exact attention☆22,361Updated this week
- Ongoing research training transformer models at scale☆15,242Feb 21, 2026Updated last week
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,766Aug 4, 2024Updated last year
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,377Jul 25, 2023Updated 2 years ago
- Aligning pretrained language models with instruction data generated by themselves.☆4,576Mar 27, 2023Updated 2 years ago
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,953Aug 9, 2025Updated 6 months ago
- O1 Replication Journey☆1,999Jan 14, 2025Updated last year
- Official Repo for Open-Reasoner-Zero☆2,084Jun 2, 2025Updated 8 months ago
- Simple RL training for reasoning☆3,829Dec 23, 2025Updated 2 months ago
- Instruction Tuning with GPT-4☆4,342Jun 11, 2023Updated 2 years ago
- Scalable toolkit for efficient model alignment☆851Oct 6, 2025Updated 4 months ago
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆391Jan 19, 2025Updated last year
- Scalable RL solution for advanced reasoning of language models☆1,806Mar 18, 2025Updated 11 months ago
- Fully open reproduction of DeepSeek-R1☆25,890Nov 24, 2025Updated 3 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,838Jun 10, 2024Updated last year
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆30,271Jul 17, 2024Updated last year
- OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, …☆6,688Updated this week