A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
☆908Sep 30, 2025Updated 5 months ago
Alternatives and similar repositories for HALOs
Users that are interested in HALOs are comparing it to the libraries listed below
Sorting:
- Reference implementation for DPO (Direct Preference Optimization)☆2,866Aug 11, 2024Updated last year
- Robust recipes to align language models with human and AI preferences☆5,527Sep 8, 2025Updated 6 months ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆948Feb 16, 2025Updated last year
- Recipes to train reward model for RLHF.☆1,521Apr 24, 2025Updated 10 months ago
- Official repository for ORPO☆473May 31, 2024Updated last year
- RewardBench: the first evaluation tool for reward models.☆704Feb 16, 2026Updated last month
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆9,191Updated this week
- Train transformer language models with reinforcement learning.☆17,697Updated this week
- [NIPS2023] RRHF & Wombat☆808Sep 22, 2023Updated 2 years ago
- A large-scale, fine-grained, diverse preference dataset (and models).☆364Dec 29, 2023Updated 2 years ago
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,234May 8, 2024Updated last year
- A recipe for online RLHF and online iterative DPO.☆544Dec 28, 2024Updated last year
- Scalable toolkit for efficient model alignment☆851Oct 6, 2025Updated 5 months ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆591Dec 9, 2024Updated last year
- AllenAI's post-training codebase☆3,629Updated this week
- A framework for few-shot evaluation of language models.☆11,704Mar 5, 2026Updated 2 weeks ago
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,961Aug 9, 2025Updated 7 months ago
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,739Jan 8, 2024Updated 2 years ago
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆842Jul 1, 2024Updated last year
- Tools for merging pretrained large language models.☆6,867Mar 15, 2026Updated last week
- ☆16Jul 23, 2024Updated last year
- Scalable RL solution for advanced reasoning of language models☆1,821Mar 18, 2025Updated last year
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,131Updated this week
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,331Dec 9, 2025Updated 3 months ago
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆392Jan 19, 2025Updated last year
- verl: Volcano Engine Reinforcement Learning for LLMs☆19,919Updated this week
- Official Repo for Open-Reasoner-Zero☆2,086Jun 2, 2025Updated 9 months ago
- Minimalistic large language model 3D-parallelism training☆2,617Feb 19, 2026Updated last month
- A modular RL library to fine-tune language models to human preferences☆2,382Mar 1, 2024Updated 2 years ago
- Simple RL training for reasoning☆3,841Dec 23, 2025Updated 2 months ago
- Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]☆149Oct 27, 2024Updated last year
- Arena-Hard-Auto: An automatic LLM benchmark.☆1,008Jun 21, 2025Updated 9 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,232Aug 27, 2025Updated 6 months ago
- Democratizing Reinforcement Learning for LLMs☆5,259Updated this week
- YaRN: Efficient Context Window Extension of Large Language Models☆1,685Apr 17, 2024Updated last year
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆56Jun 16, 2024Updated last year
- ☆314Jun 9, 2024Updated last year
- ☆19Oct 2, 2023Updated 2 years ago
- [ACL 2025, Main Conference, Oral] Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process☆30Aug 2, 2024Updated last year