[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
☆956Feb 16, 2025Updated last year
Alternatives and similar repositories for SimPO
Users that are interested in SimPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Reference implementation for DPO (Direct Preference Optimization)☆2,898Aug 11, 2024Updated last year
- Robust recipes to align language models with human and AI preferences☆5,643May 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
- Recipes to train reward model for RLHF.☆1,534Apr 24, 2025Updated last year
- Reference implementation for Token-level Direct Preference Optimization(TDPO)☆156Feb 14, 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.
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,841Jul 14, 2026Updated last week
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆2,007Aug 9, 2025Updated 11 months ago
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆398Jan 19, 2025Updated last year
- Official repository for ORPO☆480May 31, 2024Updated 2 years ago
- Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"☆41Sep 24, 2024Updated last year
- This repository contains the joint use of CPO and SimPO method for better reference-free preference learning methods.☆59Aug 13, 2024Updated last year
- RewardBench: the first evaluation tool for reward models.☆727Feb 16, 2026Updated 5 months ago
- AllenAI's post-training codebase☆3,807Updated this week
- A recipe for online RLHF and online iterative DPO.☆544Dec 28, 2024Updated 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.
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,247May 8, 2024Updated 2 years ago
- Train transformer language models with reinforcement learning.☆18,913Updated this week
- Arena-Hard-Auto: An automatic LLM benchmark.☆1,050Jun 21, 2025Updated last year
- Simple RL training for reasoning☆3,869Dec 23, 2025Updated 7 months ago
- [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data …☆874Mar 17, 2025Updated last year
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,611Nov 24, 2025Updated 8 months ago
- ☆1,170Jan 10, 2026Updated 6 months ago
- Benchmarking LLMs with Challenging Tasks from Real Users☆255Nov 3, 2024Updated last year
- The official implementation of Self-Play Preference Optimization (SPPO)☆590Jan 23, 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.
- Secrets of RLHF in Large Language Models Part I: PPO☆1,426Mar 3, 2024Updated 2 years ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,626Updated this week
- Direct preference optimization with f-divergences.☆17Nov 3, 2024Updated last year
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆600Dec 9, 2024Updated last year
- Tools for merging pretrained large language models.☆7,258Jun 17, 2026Updated last month
- Scalable toolkit for efficient model alignment☆851Oct 6, 2025Updated 9 months ago
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆532Oct 20, 2024Updated last year
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,151Jun 1, 2023Updated 3 years ago
- Scalable RL solution for advanced reasoning of language models☆1,865Mar 18, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Democratizing Reinforcement Learning for LLMs☆5,721Updated this week
- O1 Replication Journey☆2,000Jan 14, 2025Updated last year
- Official Repo for Open-Reasoner-Zero☆2,096Jun 2, 2025Updated last year
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,844May 11, 2025Updated last year
- ☆336Jul 25, 2024Updated last year
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆75May 20, 2025Updated last year
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆47Apr 15, 2025Updated last year