AllenAI's post-training codebase
☆3,726May 17, 2026Updated last 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☆6,507Nov 24, 2025Updated 5 months ago
- Robust recipes to align language models with human and AI preferences☆5,602Apr 8, 2026Updated last month
- A framework for few-shot evaluation of language models.☆12,595May 11, 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…☆9,523May 15, 2026Updated last week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆21,337May 16, 2026Updated last 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.
- Train transformer language models with reinforcement learning.☆18,411Updated this week
- Reproducible, flexible LLM evaluations☆372Mar 24, 2026Updated last month
- Simple RL training for reasoning☆3,859Dec 23, 2025Updated 5 months ago
- Minimalistic large language model 3D-parallelism training☆2,698Apr 7, 2026Updated last month
- Data and tools for generating and inspecting OLMo pre-training data.☆1,499Nov 5, 2025Updated 6 months ago
- Official Repo for Open-Reasoner-Zero☆2,091Jun 2, 2025Updated 11 months ago
- Tools for merging pretrained large language models.☆7,083May 6, 2026Updated 2 weeks ago
- Scalable RL solution for advanced reasoning of language models☆1,859Mar 18, 2025Updated last year
- Scalable toolkit for efficient model alignment☆854Oct 6, 2025Updated 7 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,128Jun 1, 2023Updated 2 years ago
- Democratizing Reinforcement Learning for LLMs☆5,548Updated this 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.☆1,985Aug 9, 2025Updated 9 months ago
- Evaluation suite for LLMs☆379Jul 11, 2025Updated 10 months ago
- Ongoing research training transformer models at scale☆16,427Updated this week
- Fully open reproduction of DeepSeek-R1☆26,020Apr 2, 2026Updated last month
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,426Updated this week
- ☆1,144Jan 10, 2026Updated 4 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Minimal reproduction of DeepSeek R1-Zero☆13,104Feb 27, 2026Updated 2 months ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆954Feb 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.☆28,137Updated this week
- Aligning pretrained language models with instruction data generated by themselves.☆4,600Mar 27, 2023Updated 3 years ago
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,748Jan 8, 2024Updated 2 years ago
- A PyTorch native platform for training generative AI models☆5,362Updated this week
- Recipes to train reward model for RLHF.☆1,531Apr 24, 2025Updated last year
- O1 Replication Journey☆2,000Jan 14, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A high-throughput and memory-efficient inference and serving engine for LLMs☆80,418Updated this week
- Reference implementation for DPO (Direct Preference Optimization)☆2,890Aug 11, 2024Updated last year
- Go ahead and axolotl questions☆11,938Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,229Updated this week
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆39,474May 1, 2026Updated 3 weeks ago
- Fast and memory-efficient exact attention☆23,836May 16, 2026Updated last week
- RewardBench: the first evaluation tool for reward models.☆715Feb 16, 2026Updated 3 months ago