AllenAI's post-training codebase
☆3,942Nov 21, 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☆6,740Nov 24, 2025Updated 11 months ago
- Reproducible, flexible LLM evaluations☆413Mar 24, 2026Updated 7 months ago
- Robust recipes to align language models with human and AI preferences☆5,716Sep 23, 2026Updated last month
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,173Nov 3, 2026Updated 2 weeks ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆24,302Updated this week
- 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.
- Train transformer language models with reinforcement learning.☆19,788Updated this week
- A framework for few-shot evaluation of language models.☆14,515Nov 4, 2026Updated 2 weeks ago
- PyTorch building blocks for the OLMo ecosystem☆1,810Updated this week
- Simple RL training for reasoning☆3,878Dec 23, 2025Updated 10 months ago
- Democratizing Reinforcement Learning for LLMs☆5,927Oct 16, 2026Updated last month
- slime is an LLM training framework for RL Scaling.☆8,856Nov 5, 2026Updated 2 weeks ago
- Data and tools for generating and inspecting OLMo pre-training data.☆1,564Aug 24, 2026Updated 2 months ago
- Minimalistic large language model 3D-parallelism training☆2,869Oct 8, 2026Updated last month
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,546Updated this week
- 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.
- Official Repo for Open-Reasoner-Zero☆2,103Jun 2, 2025Updated last year
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,587Updated this week
- Ongoing research training transformer models at scale☆18,451Updated this week
- Tools for merging pretrained large language models.☆7,485Oct 31, 2026Updated 3 weeks ago
- Scalable RL solution for advanced reasoning of language models☆1,871Mar 18, 2025Updated last year
- Fully open reproduction of DeepSeek-R1☆26,485Oct 26, 2026Updated 3 weeks ago
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆2,026Aug 9, 2025Updated last year
- ☆1,208Jan 10, 2026Updated 10 months ago
- A PyTorch native platform for training generative AI models☆5,937Updated this week
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,777Aug 4, 2024Updated 2 years ago
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,152Jun 1, 2023Updated 3 years ago
- Evaluation suite for LLMs☆380Jul 11, 2025Updated last year
- Scalable toolkit for efficient model alignment☆851Oct 6, 2025Updated last year
- Minimal reproduction of DeepSeek R1-Zero☆13,259Feb 27, 2026Updated 8 months ago
- Our library for RL environments + evals☆4,798Updated this week
- Reference implementation for DPO (Direct Preference Optimization)☆2,923Aug 11, 2024Updated 2 years ago
- Agentic RL Training at Scale☆2,268Updated this week
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,755Jan 8, 2024Updated 2 years 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.
- Go ahead and axolotl questions☆12,742Updated this week
- LLM training code for Databricks foundation models☆4,460Mar 25, 2026Updated 7 months ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,467Updated this week
- Recipes to train reward model for RLHF.☆1,546Apr 24, 2025Updated last year
- PyTorch native post-training library☆5,820Updated this week
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆964Feb 16, 2025Updated last year
- DataComp for Language Models☆1,479Sep 9, 2025Updated last year
Are these results useful?