Fully open reproduction of DeepSeek-R1
☆26,433Apr 2, 2026Updated 4 months ago
Alternatives and similar repositories for open-r1
Users that are interested in open-r1 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Minimal reproduction of DeepSeek R1-Zero☆13,226Feb 27, 2026Updated 5 months ago
- Simple RL training for reasoning☆3,870Dec 23, 2025Updated 7 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,949Updated this week
- Train transformer language models with reinforcement learning.☆19,066Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,908Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆74,064Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,785Updated this week
- ☆91,976Jun 27, 2025Updated last year
- Reproduce R1 Zero on Logic Puzzle☆2,449Mar 20, 2025Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆88,970Updated this week
- Witness the aha moment of VLM with less than $3.☆4,061May 19, 2025Updated last year
- s1: Simple test-time scaling☆6,663Jun 25, 2025Updated last year
- ☆104,188Aug 28, 2025Updated 11 months ago
- Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.☆71,049Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Official Repo for Open-Reasoner-Zero☆2,097Jun 2, 2025Updated last year
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆5,113Jul 30, 2026Updated 2 weeks ago
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL…☆15,154Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆31,752Updated this week
- Fast and memory-efficient exact attention☆24,701Updated this week
- A fork to add multimodal model training to open-r1☆1,600Feb 8, 2025Updated last year
- A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.☆6,899Dec 17, 2025Updated 7 months ago
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆27,505Jan 9, 2026Updated 7 months ago
- slime is an LLM post-training framework for RL Scaling.☆7,885Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Solve Visual Understanding with Reinforced VLMs☆6,016Jul 7, 2026Updated last month
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆42,926Updated this week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆21,543Updated this week
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆39,518May 1, 2026Updated 3 months ago
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆12,841Jul 28, 2026Updated 2 weeks ago
- A framework for few-shot evaluation of language models.☆13,616Updated this week
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,768Jul 24, 2026Updated 2 weeks ago
- Ongoing research training transformer models at scale☆17,419Updated this week
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆19,779Jan 30, 2026Updated 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.
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,367Updated this week
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆24,977Aug 12, 2024Updated 2 years ago
- Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL☆5,292Nov 13, 2025Updated 9 months ago
- Fully open data curation for reasoning models☆2,315Dec 2, 2025Updated 8 months ago
- 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal model…☆164,062Updated this week
- Janus-Series: Unified Multimodal Understanding and Generation Models☆17,753Feb 1, 2025Updated last year
- Sky-T1: Train your own O1 preview model within $450☆3,398Jul 12, 2025Updated last year