AllenAI's post-training codebase
☆3,827Aug 11, 2026Updated this week
Alternatives and similar repositories for open-instruct
Users that are interested in open-instruct are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Modeling, training, eval, and inference code for OLMo☆6,623Nov 24, 2025Updated 8 months ago
- Robust recipes to align language models with human and AI preferences☆5,658May 26, 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…☆9,901Jul 14, 2026Updated 3 weeks ago
- A framework for few-shot evaluation of language models.☆13,595Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,918Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Train transformer language models with reinforcement learning.☆19,048Updated this week
- Reproducible, flexible LLM evaluations☆391Mar 24, 2026Updated 4 months ago
- Simple RL training for reasoning☆3,871Dec 23, 2025Updated 7 months ago
- Minimalistic large language model 3D-parallelism training☆2,782May 26, 2026Updated 2 months ago
- Data and tools for generating and inspecting OLMo pre-training data.☆1,534Nov 5, 2025Updated 9 months ago
- Democratizing Reinforcement Learning for LLMs☆5,778Updated this week
- Official Repo for Open-Reasoner-Zero☆2,098Jun 2, 2025Updated last year
- Tools for merging pretrained large language models.☆7,287Jun 17, 2026Updated last month
- Scalable RL solution for advanced reasoning of language models☆1,869Mar 18, 2025Updated last year
- 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.
- Scalable toolkit for efficient model alignment☆853Oct 6, 2025Updated 10 months ago
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,150Jun 1, 2023Updated 3 years ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,515Updated this week
- slime is an LLM post-training framework for RL Scaling.☆7,853Updated this week
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,774Aug 4, 2024Updated 2 years ago
- ☆1,175Jan 10, 2026Updated 7 months ago
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆2,011Aug 9, 2025Updated last year
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,144Updated this week
- Evaluation suite for LLMs☆378Jul 11, 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.
- Ongoing research training transformer models at scale☆17,393Updated this week
- LLM training code for Databricks foundation models☆4,438Mar 25, 2026Updated 4 months ago
- Fully open reproduction of DeepSeek-R1☆26,432Apr 2, 2026Updated 4 months ago
- Minimal reproduction of DeepSeek R1-Zero☆13,226Feb 27, 2026Updated 5 months ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆601Dec 9, 2024Updated last year
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆958Feb 16, 2025Updated last year
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,752Jan 8, 2024Updated 2 years ago
- Aligning pretrained language models with instruction data generated by themselves.☆4,610Mar 27, 2023Updated 3 years ago
- Recipes to train reward model for RLHF.☆1,539Apr 24, 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.
- A PyTorch native platform for training generative AI models☆5,615Updated this week
- Reference implementation for DPO (Direct Preference Optimization)☆2,904Aug 11, 2024Updated 2 years ago
- O1 Replication Journey☆2,001Jan 14, 2025Updated last year
- Go ahead and axolotl questions☆12,338Updated this week
- Our library for RL environments + evals☆4,496Updated this week
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆39,519May 1, 2026Updated 3 months ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,362Updated this week