https://github.com/huggingface/open-r1

\n

This organization is dedicated to:

\n

\n
• Sharing datasets and models built on the path to replicating DeepSeek-R1.
\n
• Fostering meaningful discussions and collaboration in the Community tab.
\n

\n

By working together, we aim to create a robust foundation for reasoning models that the entire research and industry community can leverage.

\n

Plan of attack

\n

We are using the DeepSeek-R1 tech report as a guide to recreate their pipeline. The work can be broken down into three main steps:

\n

\n
• Replicate R1-Distill:\nDistill a high-quality reasoning corpus from DeepSeek-R1 to create the R1-Distill models.
\n
• Recreate the pure RL pipeline:\nReproduce the reinforcement learning process that DeepSeek used to train R1-Zero. This will likely require curating new, large-scale datasets for math, reasoning, and code.
\n
• Demonstrate end-to-end training:\nShow that we can go from a base model to RL-tuned reasoning capabilities through a multi-stage training approach, combining supervised fine-tuning (SFT) and reinforcement learning (RL).
\n

\n

How to contribute

\n

This project thrives on community participation! Here are some ways you can contribute:

\n

\n
• Join the discussion: Share ideas, ask questions, and collaborate with others in the Community tab.
\n
• Contribute code or datasets: Submit pull requests with datasets, models, or improvements to the pipeline.
\n
• Experiment and share results: Try out different approaches and share your findings with the community.
\n

\n

Let’s build something impactful together. 🚀

\n","classNames":"hf-sanitized hf-sanitized-XgXq1rZcBaEyTD1EiVzQH"},"users":[{"_id":"5f0c746619cb630495b814fd","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1594651707950-noauth.jpeg","isPro":true,"fullname":"Lewis Tunstall","user":"lewtun","type":"user"},{"_id":"61c141342aac764ce1654e43","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61c141342aac764ce1654e43/81AwoT5IQ_Xdw0OVw7TKu.jpeg","isPro":false,"fullname":"Loubna Ben Allal","user":"loubnabnl","type":"user"},{"_id":"651e96991b97c9f33d26bde6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/-Bqs6qrmz0yCfwtB2e-6q.jpeg","isPro":false,"fullname":"Elie Bakouch","user":"eliebak","type":"user"},{"_id":"61b85ce86eb1f2c5e6233736","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1655385361868-61b85ce86eb1f2c5e6233736.jpeg","isPro":true,"fullname":"Vaibhav Srivastav","user":"reach-vb","type":"user"},{"_id":"6435d564a4bd75c62cc03701","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6435d564a4bd75c62cc03701/7P2G_wVNB6MISp2Phh427.jpeg","isPro":false,"fullname":"Agustín Piqueres Lajarín","user":"plaguss","type":"user"},{"_id":"626ede24d2fa9e7d598c8709","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/626ede24d2fa9e7d598c8709/JKS8-Y2Jw87EgNQZBRswq.jpeg","isPro":true,"fullname":"Hynek Kydlicek","user":"hynky","type":"user"},{"_id":"6202a599216215a22221dea9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1644340617257-noauth.png","isPro":false,"fullname":"Clémentine Fourrier","user":"clefourrier","type":"user"},{"_id":"60f2fc91b92afccb7c34b8ed","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f2fc91b92afccb7c34b8ed/W2-Nay12Ef4Ltyaf8EKE9.jpeg","isPro":false,"fullname":"Gabriel Martín Blázquez","user":"gabrielmbmb","type":"user"},{"_id":"61914f536d34e827404ceb99","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1643012094339-61914f536d34e827404ceb99.jpeg","isPro":false,"fullname":"hysts","user":"hysts","type":"user"},{"_id":"6340651b388c3fa40f9a5bc0","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6340651b388c3fa40f9a5bc0/av1C4_S7bHGxAzOu8lOmG.jpeg","isPro":false,"fullname":"Adam Molnar","user":"lunarflu","type":"user"},{"_id":"6200d0a443eb0913fa2df7cc","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1644220542819-noauth.jpeg","isPro":false,"fullname":"Edward Beeching","user":"edbeeching","type":"user"},{"_id":"5df7e9e5da6d0311fd3d53f9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1583857746553-5df7e9e5da6d0311fd3d53f9.jpeg","isPro":true,"fullname":"Thomas Wolf","user":"thomwolf","type":"user"},{"_id":"629f3b18ee05727ce328ccbe","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1669189789447-629f3b18ee05727ce328ccbe.jpeg","isPro":false,"fullname":"Kashif Rasul","user":"kashif","type":"user"},{"_id":"65d66b494bbd0d92b641cdbb","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65d66b494bbd0d92b641cdbb/6-7dm7B-JxcoS1QlCPdMN.jpeg","isPro":false,"fullname":"Andres Marafioti","user":"andito","type":"user"},{"_id":"6632d7e22c4f4bfc3f6a05c2","avatarUrl":"/avatars/8de694cf8680c548dd8301615437aacd.svg","isPro":false,"fullname":"Mohamed Mekkouri","user":"medmekk","type":"user"},{"_id":"620a77b7dbba8fc1fbb8bdb4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620a77b7dbba8fc1fbb8bdb4/ZRW2pH9Iawj700OyLpJl8.png","isPro":false,"fullname":"Florent Gbelidji","user":"florentgbelidji","type":"user"},{"_id":"60f0608166e5701b80ed3f02","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/BHso-wSWpR9b8b8CKvodC.jpeg","isPro":true,"fullname":"Alvaro Bartolome","user":"alvarobartt","type":"user"},{"_id":"62d648291fa3e4e7ae3fa6e8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62d648291fa3e4e7ae3fa6e8/oatOwf8Xqe5eDbCSuYqCd.png","isPro":false,"fullname":"ben burtenshaw","user":"burtenshaw","type":"user"},{"_id":"602e6dee60e3dd96631c906e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1613655355830-noauth.png","isPro":false,"fullname":"Anton Lozhkov","user":"anton-l","type":"user"},{"_id":"62596f9e1c0a084224b93e00","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62596f9e1c0a084224b93e00/X2aLkJ0ofhkXwAg7lXvxD.jpeg","isPro":false,"fullname":"Guilherme Penedo","user":"guipenedo","type":"user"},{"_id":"5ee3a7cd2a3eae3cbdad1305","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1594144055859-5ee3a7cd2a3eae3cbdad1305.jpeg","isPro":false,"fullname":"Yacine Jernite","user":"yjernite","type":"user"},{"_id":"660ed80b1889bf2cd53cab7f","avatarUrl":"/avatars/93ee6ff00668c2698ad8b6fa6f072b92.svg","isPro":false,"fullname":"Haojun Zhao","user":"zzhhjjj","type":"user"},{"_id":"66ba71a4447411b9c0e19d71","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/4f93ZrYdaKfK3F53IB51x.jpeg","isPro":false,"fullname":"Cyril","user":"cyrilzakka","type":"user"},{"_id":"648a374f00f7a3374ee64b99","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/648a374f00f7a3374ee64b99/YPwSOrronoozwHbJchPn3.jpeg","isPro":true,"fullname":"Caleb Fahlgren","user":"cfahlgren1","type":"user"},{"_id":"5ff8c9f4b2035d9a81a859f7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1652134289581-5ff8c9f4b2035d9a81a859f7.jpeg","isPro":false,"fullname":"Nouamane Tazi","user":"nouamanetazi","type":"user"},{"_id":"631ce4b244503b72277fc89f","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1677431596830-631ce4b244503b72277fc89f.jpeg","isPro":false,"fullname":"Quentin Gallouédec","user":"qgallouedec","type":"user"},{"_id":"5e48005437cb5b49818287a5","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5e48005437cb5b49818287a5/4uCXGGui-9QifAT4qelxU.png","isPro":false,"fullname":"Leandro von Werra","user":"lvwerra","type":"user"},{"_id":"63e0eea7af523c37e5a77966","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg","isPro":false,"fullname":"Nathan Habib","user":"SaylorTwift","type":"user"},{"_id":"63691c3eda9b693c2730b2a2","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63691c3eda9b693c2730b2a2/hBtKpgo3_9003MWCGkw5d.png","isPro":false,"fullname":"Brigitte Tousignant","user":"BrigitteTousi","type":"user"},{"_id":"60107b385ac3e86b3ea4fc34","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1627505688463-60107b385ac3e86b3ea4fc34.jpeg","isPro":true,"fullname":"Daniel van Strien","user":"davanstrien","type":"user"},{"_id":"647f36a8454af0237bd49574","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/647f36a8454af0237bd49574/jshkqBUTY-GZL8As8y6Aq.jpeg","isPro":false,"fullname":"Florent Daudens","user":"fdaudens","type":"user"},{"_id":"63d10d4e8eaa4831005e92b5","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63d10d4e8eaa4831005e92b5/7p7-OmWM6PqqCs7ZStPGD.jpeg","isPro":false,"fullname":"Aymeric Roucher","user":"m-ric","type":"user"}],"collections":[{"slug":"open-r1/olympiccoder-67d0927b5ee0dde083bed8cd","title":"👩‍💻 OlympicCoder","description":"Reasoning datasets and models for competitive coding","gating":false,"lastUpdated":"2025-03-11T19:46:50.262Z","owner":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"items":[{"_id":"67d0931ceb98fb8ac5cd11b7","position":0,"type":"dataset","note":{"html":"Problem statements for CodeForces problems","text":"Problem statements for CodeForces problems"},"author":"open-r1","downloads":340,"gated":false,"id":"open-r1/codeforces","lastModified":"2025-03-11T20:37:12.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10024,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":17,"isLikedByUser":false},{"_id":"67d092a4f1e8655c93f8e9d0","position":1,"type":"dataset","note":{"html":"Chain of Thought generations from DeepSeek-R1 on 10k CodeForces problems\n","text":"Chain of Thought generations from DeepSeek-R1 on 10k CodeForces problems\n"},"author":"open-r1","downloads":783,"gated":false,"id":"open-r1/codeforces-cots","lastModified":"2025-03-13T14:50:43.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":195191,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":30,"isLikedByUser":false},{"_id":"67d092987712ab2e1dd26b6f","position":2,"type":"model","note":{"html":"A fine-tuned version of Qwen2.5-Coder-7B-Instruct on the codeforces-cots dataset","text":"A fine-tuned version of Qwen2.5-Coder-7B-Instruct on the codeforces-cots dataset"},"author":"open-r1","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"downloads":641,"gated":false,"id":"open-r1/OlympicCoder-7B","availableInferenceProviders":[],"lastModified":"2025-03-13T15:32:02.000Z","likes":84,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[]},{"_id":"67d0929e41dc6a1f4f07e603","position":3,"type":"model","note":{"html":"A fine-tuned version of Qwen2.5-Coder-32B-Instruct on the codeforces-cots dataset","text":"A fine-tuned version of Qwen2.5-Coder-32B-Instruct on the codeforces-cots dataset"},"author":"open-r1","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"downloads":434,"gated":false,"id":"open-r1/OlympicCoder-32B","availableInferenceProviders":[],"lastModified":"2025-03-13T15:34:09.000Z","likes":67,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[]}],"position":1,"theme":"orange","private":false,"shareUrl":"https://huggingface.co/collections/open-r1/olympiccoder-67d0927b5ee0dde083bed8cd","upvotes":8,"isUpvotedByUser":false},{"slug":"open-r1/ioi-67cee324e60b1346a6ab73e2","title":"🏆 IOI","description":"Resources related to International Olympiad in Informatics (IOI) problems","gating":false,"lastUpdated":"2025-03-11T19:45:51.923Z","owner":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"items":[{"_id":"67cee3726a1b139d804e1006","position":0,"type":"dataset","note":{"html":"The IOI dataset, covering problems from IOI'2020 to IOI'2024","text":"The IOI dataset, covering problems from IOI'2020 to IOI'2024"},"author":"open-r1","downloads":249,"gated":false,"id":"open-r1/ioi","lastModified":"2025-03-12T23:34:52.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":270,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":4,"isLikedByUser":false},{"_id":"67cee395366ebf6bc2a4ffc7","position":1,"type":"dataset","note":{"html":"Test cases for open-r1/ioi","text":"Test cases for open-r1/ioi"},"author":"open-r1","downloads":170,"gated":false,"id":"open-r1/ioi-test-cases","lastModified":"2025-03-12T23:40:30.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":4240,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":3,"isLikedByUser":false},{"_id":"67cee3a40fee64920a31fde9","position":2,"type":"dataset","note":{"html":"Official solutions (source code) from the IOI organizers, and their scores. Meant as a reference/for ground truth solutions","text":"Official solutions (source code) from the IOI organizers, and their scores. Meant as a reference/for ground truth solutions"},"author":"open-r1","downloads":84,"gated":false,"id":"open-r1/ioi-sample-solutions","lastModified":"2025-03-09T02:02:45.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":5225,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":2,"isLikedByUser":false},{"_id":"67d0455448276ed25e07c9b1","position":3,"type":"dataset","note":{"html":"Model generated solutions and their evaluation for IOI'2024\n","text":"Model generated solutions and their evaluation for IOI'2024\n"},"author":"open-r1","downloads":102,"gated":false,"id":"open-r1/ioi-2024-model-solutions","lastModified":"2025-03-12T23:29:58.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":102500,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":2,"isLikedByUser":false}],"position":2,"theme":"green","private":false,"shareUrl":"https://huggingface.co/collections/open-r1/ioi-67cee324e60b1346a6ab73e2","upvotes":3,"isUpvotedByUser":false},{"slug":"open-r1/openr1-math-67ab097f8087b6634035e764","title":"OpenR1-Math","description":"Dataset and SFT model distilled from DeepSeek-R1. Check out our blog post for more details: https://huggingface.co/blog/open-r1/update-2","gating":false,"lastUpdated":"2025-03-11T19:45:22.857Z","owner":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"items":[{"_id":"67ab09b783b1182df7c83229","position":0,"type":"dataset","author":"open-r1","downloads":53049,"gated":false,"id":"open-r1/OpenR1-Math-220k","lastModified":"2025-02-18T11:45:27.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":450258,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":491,"isLikedByUser":false},{"_id":"67ab09bd354af57d2922f46c","position":1,"type":"model","author":"open-r1","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"downloads":14132,"gated":false,"id":"open-r1/OpenR1-Qwen-7B","availableInferenceProviders":[],"lastModified":"2025-02-11T08:10:35.000Z","likes":40,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[]},{"_id":"67af880b3d2e866244346f77","position":2,"type":"dataset","author":"open-r1","downloads":2185,"gated":false,"id":"open-r1/OpenR1-Math-Raw","lastModified":"2025-02-24T15:22:26.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":516499,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":72,"isLikedByUser":false}],"position":3,"theme":"indigo","private":false,"shareUrl":"https://huggingface.co/collections/open-r1/openr1-math-67ab097f8087b6634035e764","upvotes":7,"isUpvotedByUser":false},{"slug":"open-r1/reasoning-datasets-67980cac6e816a0eda98c678","title":"🧠 Reasoning datasets","description":"Datasets with reasoning traces for math and code released by the community","gating":false,"lastUpdated":"2025-03-11T19:45:22.877Z","owner":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"items":[{"_id":"67980d02e0bae7ff702c8ec3","position":0,"type":"dataset","note":{"html":"17k reasoning traces for coding and math distilled from 🐋DeepSeek-R1","text":"17k reasoning traces for coding and math distilled from 🐋DeepSeek-R1"},"author":"bespokelabs","downloads":60725,"gated":false,"id":"bespokelabs/Bespoke-Stratos-17k","lastModified":"2025-01-31T00:00:38.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":16710,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":294,"isLikedByUser":false},{"_id":"679927e8b2366584e1402652","position":1,"type":"dataset","note":{"html":"114k reasoning traces covering math, science, code, and puzzles distilled from 🐋DeepSeek-R1","text":"114k reasoning traces covering math, science, code, and puzzles distilled from 🐋DeepSeek-R1"},"author":"open-thoughts","downloads":86587,"gated":false,"id":"open-thoughts/OpenThoughts-114k","lastModified":"2025-02-20T07:16:57.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":227914,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":652,"isLikedByUser":false},{"_id":"679d13b337b32b3c7dd1e940","position":2,"type":"dataset","note":{"html":"Filtered version of OpenThoughts-114k based on correct answers","text":"Filtered version of OpenThoughts-114k based on correct answers"},"author":"open-r1","downloads":1994,"gated":false,"id":"open-r1/OpenThoughts-114k-math","lastModified":"2025-01-30T11:05:51.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":89120,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":72,"isLikedByUser":false},{"_id":"67980ff804389cf71947edea","position":3,"type":"dataset","note":{"html":"5M reasoning traces for math problems distilled from QwQ-32B","text":"5M reasoning traces for math problems distilled from QwQ-32B"},"author":"PrimeIntellect","downloads":2440,"gated":false,"id":"PrimeIntellect/NuminaMath-QwQ-CoT-5M","lastModified":"2025-01-22T21:00:36.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":5138102,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":47,"isLikedByUser":false}],"position":4,"theme":"indigo","private":false,"shareUrl":"https://huggingface.co/collections/open-r1/reasoning-datasets-67980cac6e816a0eda98c678","upvotes":101,"isUpvotedByUser":false}],"datasets":[{"author":"open-r1","downloads":783,"gated":false,"id":"open-r1/codeforces-cots","lastModified":"2025-03-13T14:50:43.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":195191,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":30,"isLikedByUser":false},{"author":"open-r1","downloads":170,"gated":false,"id":"open-r1/ioi-test-cases","lastModified":"2025-03-12T23:40:30.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":4240,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":3,"isLikedByUser":false},{"author":"open-r1","downloads":249,"gated":false,"id":"open-r1/ioi","lastModified":"2025-03-12T23:34:52.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":270,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":4,"isLikedByUser":false},{"author":"open-r1","downloads":102,"gated":false,"id":"open-r1/ioi-2024-model-solutions","lastModified":"2025-03-12T23:29:58.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":102500,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":2,"isLikedByUser":false},{"author":"open-r1","downloads":340,"gated":false,"id":"open-r1/codeforces","lastModified":"2025-03-11T20:37:12.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10024,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":17,"isLikedByUser":false},{"author":"open-r1","downloads":162,"gated":false,"id":"open-r1/ioi-cots","lastModified":"2025-03-10T16:58:01.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":11450,"libraries":[],"formats":[],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":10,"isLikedByUser":false},{"author":"open-r1","downloads":84,"gated":false,"id":"open-r1/ioi-sample-solutions","lastModified":"2025-03-09T02:02:45.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":5225,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":2,"isLikedByUser":false},{"author":"open-r1","downloads":284,"gated":false,"id":"open-r1/verifiable-coding-problems-python_decontaminated","lastModified":"2025-03-08T14:47:11.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":27839,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":2,"isLikedByUser":false},{"author":"open-r1","downloads":255,"gated":false,"id":"open-r1/verifiable-coding-problems-python","lastModified":"2025-03-03T12:49:47.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":35735,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"open-r1","downloads":172,"gated":false,"id":"open-r1/SYNTHETIC-1-SFT-Data-Code_decontaminated","lastModified":"2025-02-24T15:24:57.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":49664,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"open-r1","downloads":2185,"gated":false,"id":"open-r1/OpenR1-Math-Raw","lastModified":"2025-02-24T15:22:26.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":516499,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":72,"isLikedByUser":false},{"author":"open-r1","downloads":247,"gated":false,"id":"open-r1/OpenThoughts-114k-Code_decontaminated","lastModified":"2025-02-24T15:21:58.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":16378,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":1,"isLikedByUser":false},{"author":"open-r1","downloads":248,"gated":false,"id":"open-r1/verifiable-coding-problems-python-10k_decontaminated","lastModified":"2025-02-24T14:26:35.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1574,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":2,"isLikedByUser":false},{"author":"open-r1","downloads":1477,"gated":false,"id":"open-r1/verifiable-coding-problems-python-10k","lastModified":"2025-02-19T08:41:45.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1800,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":6,"isLikedByUser":false},{"author":"open-r1","downloads":53049,"gated":false,"id":"open-r1/OpenR1-Math-220k","lastModified":"2025-02-18T11:45:27.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":450258,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":491,"isLikedByUser":false},{"author":"open-r1","downloads":404,"gated":false,"id":"open-r1/s1K-1.1","lastModified":"2025-02-17T14:04:32.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1000,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"open-r1","downloads":1994,"gated":false,"id":"open-r1/OpenThoughts-114k-math","lastModified":"2025-01-30T11:05:51.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":89120,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["text"]},"private":false,"repoType":"dataset","likes":72,"isLikedByUser":false}],"models":[{"author":"open-r1","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"downloads":434,"gated":false,"id":"open-r1/OlympicCoder-32B","availableInferenceProviders":[],"lastModified":"2025-03-13T15:34:09.000Z","likes":67,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[]},{"author":"open-r1","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"downloads":641,"gated":false,"id":"open-r1/OlympicCoder-7B","availableInferenceProviders":[],"lastModified":"2025-03-13T15:32:02.000Z","likes":84,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[]},{"author":"open-r1","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"downloads":14132,"gated":false,"id":"open-r1/OpenR1-Qwen-7B","availableInferenceProviders":[],"lastModified":"2025-02-11T08:10:35.000Z","likes":40,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[]}],"spaces":[{"author":"open-r1","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"colorFrom":"gray","colorTo":"red","createdAt":"2025-01-29T14:56:56.000Z","emoji":"⚡","id":"open-r1/open-r1-eval-leaderboard","lastModified":"2025-03-14T00:05:40.000Z","likes":45,"pinned":true,"private":false,"repoType":"space","runtime":{"stage":"RUNNING","hardware":{"current":"cpu-basic","requested":"cpu-basic"},"storage":null,"gcTimeout":172800,"replicas":{"current":1,"requested":1},"devMode":false,"domains":[{"domain":"open-r1-open-r1-eval-leaderboard.hf.space","stage":"READY"}],"sha":"2d96a6c17fbf3a31d8cfa31809f48b1765f1b006"},"title":"R1-distilled leaderboard","isLikedByUser":false,"originSpace":{"name":"HuggingFaceH4/lm-eval-leaderboard","author":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5f0c746619cb630495b814fd/j26aNEdiOgptZxJ6akGCC.png","fullname":"Hugging Face H4","name":"HuggingFaceH4","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":940}},"ai_short_description":"Generate a leaderboard for open-r1 models"}],"repoFilterModels":{"sortKey":"modified"},"repoFilterDatasets":{"sortKey":"modified"},"repoFilterSpaces":{"sortKey":"modified"},"lastOrgActivities":[{"time":"2025-03-14T00:05:41.302Z","user":"lewtun","userAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1594651707950-noauth.jpeg","orgAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","type":"update","repoData":{"author":"open-r1","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"colorFrom":"gray","colorTo":"red","createdAt":"2025-01-29T14:56:56.000Z","emoji":"⚡","id":"open-r1/open-r1-eval-leaderboard","lastModified":"2025-03-14T00:05:40.000Z","likes":45,"pinned":true,"private":false,"sdk":"gradio","repoType":"space","runtime":{"stage":"RUNNING","hardware":{"current":"cpu-basic","requested":"cpu-basic"},"storage":null,"gcTimeout":172800,"replicas":{"current":1,"requested":1},"devMode":false,"domains":[{"domain":"open-r1-open-r1-eval-leaderboard.hf.space","stage":"READY"}],"sha":"2d96a6c17fbf3a31d8cfa31809f48b1765f1b006"},"title":"R1-distilled leaderboard","isLikedByUser":false,"originSpace":{"name":"HuggingFaceH4/lm-eval-leaderboard","author":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5f0c746619cb630495b814fd/j26aNEdiOgptZxJ6akGCC.png","fullname":"Hugging Face H4","name":"HuggingFaceH4","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":940}},"ai_short_description":"Generate a leaderboard for open-r1 models","trendingScore":4},"repoId":"open-r1/open-r1-eval-leaderboard","repoType":"space","org":"open-r1"},{"time":"2025-03-13T15:34:10.793Z","user":"lewtun","userAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1594651707950-noauth.jpeg","orgAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","type":"update","repoData":{"author":"open-r1","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"downloads":434,"gated":false,"id":"open-r1/OlympicCoder-32B","availableInferenceProviders":[],"lastModified":"2025-03-13T15:34:09.000Z","likes":67,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[]},"repoId":"open-r1/OlympicCoder-32B","repoType":"model","org":"open-r1"},{"time":"2025-03-13T15:32:03.341Z","user":"lewtun","userAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1594651707950-noauth.jpeg","orgAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","type":"update","repoData":{"author":"open-r1","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"downloads":641,"gated":false,"id":"open-r1/OlympicCoder-7B","availableInferenceProviders":[],"lastModified":"2025-03-13T15:32:02.000Z","likes":84,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[]},"repoId":"open-r1/OlympicCoder-7B","repoType":"model","org":"open-r1"}],"acceptLanguages":["en","*"],"blogPosts":[{"_id":"67d09fcf8a16d93d05169b70","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"canonical":false,"isUpvotedByUser":false,"numCoauthors":9,"publishedAt":"2025-03-11T20:40:47.333Z","slug":"update-3","status":"published","title":"Open R1: Update #3","upvotes":197},{"_id":"67aa2480f82358a669b592bc","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"canonical":false,"isUpvotedByUser":false,"numCoauthors":6,"publishedAt":"2025-02-10T16:10:47.433Z","slug":"update-2","status":"published","title":"Open R1: Update #2","upvotes":202},{"_id":"679eb2d3fa8dcdbe6962d892","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"canonical":false,"isUpvotedByUser":false,"numCoauthors":7,"publishedAt":"2025-02-02T00:04:28.771Z","slug":"update-1","status":"published","title":"Open-R1: Update #1","upvotes":295},{"_id":"679ca61439dbdedac74c3caf","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/QG_uzb2VV3OeKO0c61ynh.png","fullname":"Open R1","name":"open-r1","type":"org","isHf":false,"isMod":false,"isEnterprise":true,"followerCount":1183},"canonical":false,"isUpvotedByUser":false,"numCoauthors":0,"publishedAt":"2025-01-31T10:29:40.828Z","slug":"mini-r1-contdown-game","status":"published","title":"Mini-R1: Reproduce Deepseek R1 „aha moment“ a RL tutorial","upvotes":43}]}">