Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Fully open reproduction of DeepSeek-R1
| Date | Stars |
|---|---|
| 2026-07-31 | 26414 |
| 2026-08-01 | 26415 |
| 2026-08-02 | 26417 |
| 2026-08-03 | 26419 |
| 2026-08-04 | 26420 |
| 2026-08-05 | 26423 |
| 2026-08-06 | 26423 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Open R1
*A fully open reproduction of DeepSeek-R1. This repo is a work in progress, let's build it together!*
**Table of Contents**
1. [Overview](#overview)
2. [Plan of attack](#plan-of-attack)
3. [Installation](#installation)
4. [Training models](#training-models)
- [SFT](#sft)
- [GRPO](#grpo)
5. [Evaluating models](#evaluating-models)
6. [Reproducing Deepseek's evaluation results](#reproducing-deepseeks-evaluation-results)
7. [Data generation](#data-generation)
- [Generate data from a smol distilled R1 model](#generate-data-from-a-smol-distilled-r1-model)
- [Generate data from DeepSeek-R1](#generate-data-from-deepseek-r1)
8. [Contributing](#contributing)
## Overview
The goal of this repo is to build the missing pieces of the R1 pipeline such that everybody can reproduce and build on top of it. The project is simple by design and mostly consists of:
- `src/open_r1`: contains the scripts to train models as well as generate synthetic data:
- `grpo.py`: trains a model with GRPO on a given dataset.
- `sft.py`: performs a simple SFT of a model on a dataset.
- `generate.py`: generates synthetic data from a model using [Distilabel](https://github.com/argilla-io/distilabel).
- `Makefile`: contains easy-to-run commands for each step in the R1 pipeline leveraging the scripts above.
### Plan of attack
We will use the DeepSeek-R1 [tech report](https://github.com/deepseek-ai/DeepSeek-R1) as a guide, which can roughly be broken down into three main steps:
* Step 1: replicate the R1-Distill models by distilling a high-quality corpus from DeepSeek-R1.
* Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will likely involve curating new, large-scale datasets for math, reasoning, and code.
* Step 3: show we can go from base model to RL-tuned via multi-stage training.
<center>
<img src="assets/plan-of-attack.png" width="500">
</center>
## News 🗞️
* **🧑🍳 [2025/05/26] (Step 1 completed!)** We release [**Mixture-of-Thoughts**](https://huggingface.co/datasets/open-r1/Mixture-of-Thoughts)--a curated reasoning dataset of 350k verified traces distilled from R1. The dataset spans tasks in mathematics, coding, and science, and is designed to teach language models to reason step-by-step. We also provide a recipe to train [OpenR1-Distill-7B](https://huggingface.co/open-r1/OpenR1-Distill-7B), which replicates the reasoning capabilities of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) and marks the completion of step 1 in the Open R1 project.
* **⚡️ [2025/03/11] [(update #3)](https://huggingface.co/blog/open-r1/update-3):** We release the [**CodeForces-CoTs**](https://huggingface.co/datasets/open-r1/codeforces-cots) dataset of 10k competitive programming problems and 100k solutions distilled from R1. We also release IOI24: a new benchmark of _very_ hard problems from international olympiads. A 7B Qwen model trained on CodeForces-CoTs can outperform Claude 3.7 Sonnet on IOI24, while a 32B model can outperform R1 itself.
* **∞ [2025/02/10] [(update #2)](https://huggingface.co/blog/open-r1/update-2):** We release the [**OpenR1-Math-220k**](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) dataset of 220k traces distilled from R1 on a new version of NuminaMath. Models trained on this dataset match the performance of DeepSeek's distilled ones.
* **🔥 [2025/02/02] [(update #1)](https://huggingface.co/blog/open-r1/update-1):** We implement the first parts of the [training](https://github.com/huggingface/open-r1?tab=readme-ov-file#training-models), [inference](https://github.com/huggingface/open-r1?tab=readme-ov-file#data-generation), and [evaluation](https://github.com/huggingface/open-r1?tab=readme-ov-file#reproducing-deepseeks-evaluation-results) pipelines. Let's go!
## Installation
> [!CAUTION]
> Libraries rely on CUDA 12.4. If you see errors related to segmentation faults, double check the Excerpt of 34,958 characters
Read on GitHub
@huggingface · Switzerland
69
Edward Beeching · Hugging Face · France
30
Quentin Gallouédec · @huggingface · Canada
16
elie · @PrimeIntellect-ai · France
8
Anton Lozhkov · Hugging Face · France
5
Gabriel Martín Blázquez · @supersonik-ai · Spain
5
5
Kashif Rasul · Germany
5
Agus · Spain
5
Matt · @huggingface · Ireland
5
3
Lewis · @EvolvingPrograms · United States
3
3
Yen-Ting Lin
2
Guilherme Penedo · HuggingFace · France
2
Hynek Kydlíček
2
María Grandury · @somosnlp · Germany
2
Zhou Shao
2
2
Marco Z · @unfoldml
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a258883a6213d2d1, llm:Description: 'Fully open reproduction of DeepSeek-R1' by Hugging Face. Likely a reproduction of a retrieval / dense retrieval or ranking model (DeepSeek) in ML. Language: Python.
matched fp:a258883a6213d2d1, llm:Description: 'Fully open reproduction of DeepSeek-R1' by Hugging Face. Likely a reproduction of a retrieval / dense retrieval or ranking model (DeepSeek) in ML. Language: Python.
matched fp:a258883a6213d2d1, llm:Description: 'Fully open reproduction of DeepSeek-R1' by Hugging Face. Likely a reproduction of a retrieval / dense retrieval or ranking model (DeepSeek) in ML. Language: Python.