AllenAI's post-training codebase
☆3,746Jun 8, 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☆6,522Nov 24, 2025Updated 6 months ago
- Robust recipes to align language models with human and AI preferences☆5,608May 26, 2026Updated 2 weeks ago
- A framework for few-shot evaluation of language models.☆12,885Jun 2, 2026Updated last week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,619Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆21,850Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Train transformer language models with reinforcement learning.☆18,613Updated this week
- Reproducible, flexible LLM evaluations☆378Mar 24, 2026Updated 2 months ago
- Simple RL training for reasoning☆3,864Dec 23, 2025Updated 5 months ago
- Minimalistic large language model 3D-parallelism training☆2,711May 26, 2026Updated 2 weeks ago
- Data and tools for generating and inspecting OLMo pre-training data.☆1,508Nov 5, 2025Updated 7 months ago
- Official Repo for Open-Reasoner-Zero☆2,096Jun 2, 2025Updated last year
- Tools for merging pretrained large language models.☆7,126May 6, 2026Updated last month
- Scalable RL solution for advanced reasoning of language models☆1,861Mar 18, 2025Updated last year
- Scalable toolkit for efficient model alignment☆851Oct 6, 2025Updated 8 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,141Jun 1, 2023Updated 3 years ago
- Democratizing Reinforcement Learning for LLMs☆5,592Jun 6, 2026Updated last week
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,773Aug 4, 2024Updated last year
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,994Aug 9, 2025Updated 10 months ago
- Evaluation suite for LLMs☆379Jul 11, 2025Updated 11 months ago
- Ongoing research training transformer models at scale☆16,617Updated this week
- Fully open reproduction of DeepSeek-R1☆26,034Apr 2, 2026Updated 2 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,437May 29, 2026Updated 2 weeks ago
- ☆1,149Jan 10, 2026Updated 5 months ago
- 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.
- Minimal reproduction of DeepSeek R1-Zero☆13,140Feb 27, 2026Updated 3 months ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆953Feb 16, 2025Updated last year
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆596Dec 9, 2024Updated last year
- SGLang is a high-performance serving framework for large language models and multimodal models.☆28,886Updated this week
- Aligning pretrained language models with instruction data generated by themselves.☆4,602Mar 27, 2023Updated 3 years ago
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,750Jan 8, 2024Updated 2 years ago
- A PyTorch native platform for training generative AI models☆5,416Jun 6, 2026Updated last week
- Recipes to train reward model for RLHF.☆1,533Apr 24, 2025Updated last year
- O1 Replication Journey☆2,000Jan 14, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A high-throughput and memory-efficient inference and serving engine for LLMs☆82,482Updated this week
- Reference implementation for DPO (Direct Preference Optimization)☆2,887Aug 11, 2024Updated last year
- Go ahead and axolotl questions☆12,032Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,240Jun 1, 2026Updated last week
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆39,470May 1, 2026Updated last month
- Fast and memory-efficient exact attention☆24,111Updated this week
- RewardBench: the first evaluation tool for reward models.☆720Feb 16, 2026Updated 3 months ago