A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
☆904Sep 30, 2025Updated 7 months ago
Alternatives and similar repositories for HALOs
Users that are interested in HALOs 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)☆2,884Aug 11, 2024Updated last year
- Robust recipes to align language models with human and AI preferences☆5,587Apr 8, 2026Updated 3 weeks ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆954Feb 16, 2025Updated last year
- Recipes to train reward model for RLHF.☆1,531Apr 24, 2025Updated last year
- Official repository for ORPO☆483May 31, 2024Updated 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.
- RewardBench: the first evaluation tool for reward models.☆713Feb 16, 2026Updated 2 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,417Updated this week
- Train transformer language models with reinforcement learning.☆18,193Updated this week
- [NIPS2023] RRHF & Wombat☆808Sep 22, 2023Updated 2 years ago
- A large-scale, fine-grained, diverse preference dataset (and models).☆367Dec 29, 2023Updated 2 years ago
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,239May 8, 2024Updated last year
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,407Apr 11, 2024Updated 2 years ago
- A recipe for online RLHF and online iterative DPO.☆544Dec 28, 2024Updated last year
- Scalable toolkit for efficient model alignment☆853Oct 6, 2025Updated 6 months 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.
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆594Dec 9, 2024Updated last year
- AllenAI's post-training codebase☆3,702Updated this week
- A framework for few-shot evaluation of language models.☆12,331Apr 22, 2026Updated last week
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,976Aug 9, 2025Updated 8 months ago
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,745Jan 8, 2024Updated 2 years ago
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆843Jul 1, 2024Updated last year
- Tools for merging pretrained large language models.☆7,023Mar 15, 2026Updated last month
- ☆16Jul 23, 2024Updated last year
- Scalable RL solution for advanced reasoning of language models☆1,852Mar 18, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,354Dec 9, 2025Updated 4 months ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,199Updated this week
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆395Jan 19, 2025Updated last year
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆20,930Apr 24, 2026Updated last week
- Official Repo for Open-Reasoner-Zero☆2,093Jun 2, 2025Updated 10 months ago
- Minimalistic large language model 3D-parallelism training☆2,674Apr 7, 2026Updated 3 weeks ago
- A modular RL library to fine-tune language models to human preferences☆2,388Mar 1, 2024Updated 2 years ago
- Simple RL training for reasoning☆3,851Dec 23, 2025Updated 4 months ago
- Arena-Hard-Auto: An automatic LLM benchmark.☆1,016Jun 21, 2025Updated 10 months ago
- 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.
- YaRN: Efficient Context Window Extension of Large Language Models☆1,708Apr 17, 2024Updated 2 years ago
- Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]☆149Oct 27, 2024Updated last year
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆56Jun 16, 2024Updated last year
- Democratizing Reinforcement Learning for LLMs☆5,462Updated this week
- ☆314Jun 9, 2024Updated last year
- ☆19Oct 2, 2023Updated 2 years ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,248Aug 27, 2025Updated 8 months ago