AllenAI's post-training codebase
☆3,677Apr 6, 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☆6,463Nov 24, 2025Updated 4 months ago
- Robust recipes to align language models with human and AI preferences☆5,551Apr 2, 2026Updated last week
- A framework for few-shot evaluation of language models.☆12,020Apr 1, 2026Updated last week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆9,315Updated this week
- verl: Volcano Engine Reinforcement Learning for LLMs☆20,603Updated this week
- NordVPN Special Discount Offer • AdSave on top-rated NordVPN 1 or 2-year plans with secure browsing, privacy protection, and support for for all major platforms.
- Train transformer language models with reinforcement learning.☆17,967Updated this week
- Reproducible, flexible LLM evaluations☆359Mar 24, 2026Updated 2 weeks ago
- Minimalistic large language model 3D-parallelism training☆2,644Updated this week
- Simple RL training for reasoning☆3,846Dec 23, 2025Updated 3 months ago
- Data and tools for generating and inspecting OLMo pre-training data.☆1,476Nov 5, 2025Updated 5 months ago
- Official Repo for Open-Reasoner-Zero☆2,089Jun 2, 2025Updated 10 months ago
- Tools for merging pretrained large language models.☆6,945Mar 15, 2026Updated 3 weeks ago
- Scalable RL solution for advanced reasoning of language models☆1,841Mar 18, 2025Updated last year
- Scalable toolkit for efficient model alignment☆852Oct 6, 2025Updated 6 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,115Jun 1, 2023Updated 2 years ago
- Democratizing Reinforcement Learning for LLMs☆5,402Updated this week
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,770Aug 4, 2024Updated last year
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,964Aug 9, 2025Updated 8 months ago
- Evaluation suite for LLMs☆379Jul 11, 2025Updated 9 months ago
- Ongoing research training transformer models at scale☆15,985Updated this week
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,374Updated this week
- Fully open reproduction of DeepSeek-R1☆25,973Apr 2, 2026Updated last week
- ☆1,126Jan 10, 2026Updated 3 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.
- Minimal reproduction of DeepSeek R1-Zero☆13,038Feb 27, 2026Updated last month
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆948Feb 16, 2025Updated last year
- SGLang is a high-performance serving framework for large language models and multimodal models.☆25,643Updated this week
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆592Dec 9, 2024Updated last year
- Aligning pretrained language models with instruction data generated by themselves.☆4,586Mar 27, 2023Updated 3 years ago
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,743Jan 8, 2024Updated 2 years ago
- A PyTorch native platform for training generative AI models☆5,220Updated this week
- Recipes to train reward model for RLHF.☆1,527Apr 24, 2025Updated 11 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆75,637Updated this week
- 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.
- O1 Replication Journey☆1,999Jan 14, 2025Updated last year
- Reference implementation for DPO (Direct Preference Optimization)☆2,876Aug 11, 2024Updated last year
- Go ahead and axolotl questions☆11,608Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,158Updated this week
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆39,447Jun 2, 2025Updated 10 months ago
- Fast and memory-efficient exact attention☆23,185Updated this week
- RewardBench: the first evaluation tool for reward models.☆707Feb 16, 2026Updated last month