\n\nILLUIN Technology is proud to release the **ViDoRe V3 benchmark**, designed and developed with contributions from NVIDIA. ViDoRe V3 is our latest benchmark, engineered to set a new industry gold standard for multi-modal, enterprise document retrieval evaluation. It addresses a critical challenge in production RAG systems: retrieving accurate information from complex, visually-rich documents.\n\nViDoRe V3 improves on existing RAG benchmarks by prioritizing enterprise relevance and rigorous data quality. Instead of relying on clean academic texts, the benchmark draws from 10 challenging, real-world datasets spanning diverse industrial domains, with 8 publicly released and 2 kept private. In addition, while previous benchmarks often rely on synthetically generated data, ViDoRe V3 features human-created and human-verified annotations.\n\nThis benchmark contains 26,000 pages and 3,099 queries translated into 6 languages. Each query is linked to retrieval ground truth data created and verified by human annotators: relevant pages, precise bounding box annotations for key elements, and a comprehensive reference answer.\n\n---\n\n# 👀 ColPali: Efficient Document Retrieval with Vision Language Models\n[](https://arxiv.org/abs/2407.01449)\n\n\n\nDocuments are visually rich structures that convey information through text, as well as tables, figures, page layouts, or fonts.\nWhile modern document retrieval systems exhibit strong performance on query-to-text matching, they struggle to exploit visual cues efficiently, hindering their performance on practical document retrieval applications such as Retrieval Augmented Generation.\nTo benchmark current systems on visually rich document retrieval, we introduce the Visual Document Retrieval Benchmark *ViDoRe*, composed of various page-level retrieving tasks spanning multiple domains, languages, and settings.\nThe inherent shortcomings of modern systems motivate the introduction of a new retrieval model architecture, *ColPali*, which leverages the document understanding capabilities of recent Vision Language Models to produce high-quality contextualized embeddings solely from images of document pages.\nCombined with a late interaction matching mechanism, *ColPali* largely outperforms modern document retrieval pipelines while being drastically faster and end-to-end trainable.\n\n---\n\n## Contact\n\n- Quentin Macé: `quentin.mace@illuin.tech`\n\n---\n\n## Citation\n\nIf you use any datasets or models from this organization in your research, please cite the original dataset as follows:\n\n```latex\n@misc{faysse2024colpaliefficientdocumentretrieval,\n title={ColPali: Efficient Document Retrieval with Vision Language Models}, \n author={Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and Céline Hudelot and Pierre Colombo},\n year={2024},\n eprint={2407.01449},\n archivePrefix={arXiv},\n primaryClass={cs.IR},\n url={https://arxiv.org/abs/2407.01449},\n}\n\n@misc{macé2025vidorebenchmarkv2raising,\n title={ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval}, \n author={Quentin Macé and António Loison and Manuel Faysse},\n year={2025},\n eprint={2505.17166},\n archivePrefix={arXiv},\n primaryClass={cs.IR},\n url={https://arxiv.org/abs/2505.17166}, \n}\n\n@misc{loison2026vidorev3comprehensiveevaluation,\n title={ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios}, \n author={António Loison and Quentin Macé and Antoine Edy and Victor Xing and Tom Balough and Gabriel Moreira and Bo Liu and Manuel Faysse and Céline Hudelot and Gautier Viaud},\n year={2026},\n eprint={2601.08620},\n archivePrefix={arXiv},\n primaryClass={cs.AI},\n url={https://arxiv.org/abs/2601.08620}, \n}\n```\n\n---\n\n## Acknowledgments\n\nThis work is partially supported by [ILLUIN Technology](https://www.illuin.tech/). \n\n","html":"\n\n

ViDoRe: Visual Document Retrieval 👀

\n\n

\n

ViDoRe V3 : our new benchmark release!

\n

Developed by ILLUIN Technology and with contributions from NVIDIA, it is the most diverse visual document retrieval benchmark to date for enterprise applications.\nIt includes 10 datasets, 26,000+ pages, 3000+ queries in 6 languages.\nCheck out : the paper or the blogpost!

\n

\n

This organization contains models, datasets, benchmarks and code released with the ViDoRe project by Illuin Technology.

\n

\n

• Leaderboard:

  \n
  \n
  • ViDoRe Leaderboard
  \n
  \n
\n

• Benchmarks:

  \n
  \n
  • ViDoRe V1 (paper, blogpost, dataset collection)
  \n
  • ViDoRe V2 (paper, blogpost, dataset collection)
  \n
  • ViDoRe V3 (paper, blogpost, dataset collection)
  \n
  \n
\n

• Models:

  \n
  \n
  • ColPali (latest: v1.3)
  \n
  • ColQwen2 (latest: v1.0)
  \n
  • ColQwen2.5 (latest: v0.2)
  \n
  • ColSmol (256M & 500M)
  \n
  • ModernVBERT (latest: v1.0)
  \n
  \n
\n

\n

---

\n

👷‍♂️ ViDoRe V3: A comprehensive evaluation of Retrieval for enterprise use-cases

\n

\n\n\n

ILLUIN Technology is proud to release the ViDoRe V3 benchmark, designed and developed with contributions from NVIDIA. ViDoRe V3 is our latest benchmark, engineered to set a new industry gold standard for multi-modal, enterprise document retrieval evaluation. It addresses a critical challenge in production RAG systems: retrieving accurate information from complex, visually-rich documents.

\n

ViDoRe V3 improves on existing RAG benchmarks by prioritizing enterprise relevance and rigorous data quality. Instead of relying on clean academic texts, the benchmark draws from 10 challenging, real-world datasets spanning diverse industrial domains, with 8 publicly released and 2 kept private. In addition, while previous benchmarks often rely on synthetically generated data, ViDoRe V3 features human-created and human-verified annotations.

\n

This benchmark contains 26,000 pages and 3,099 queries translated into 6 languages. Each query is linked to retrieval ground truth data created and verified by human annotators: relevant pages, precise bounding box annotations for key elements, and a comprehensive reference answer.

\n

---

\n

👀 ColPali: Efficient Document Retrieval with Vision Language Models

\n

\n\n\n

Documents are visually rich structures that convey information through text, as well as tables, figures, page layouts, or fonts.\nWhile modern document retrieval systems exhibit strong performance on query-to-text matching, they struggle to exploit visual cues efficiently, hindering their performance on practical document retrieval applications such as Retrieval Augmented Generation.\nTo benchmark current systems on visually rich document retrieval, we introduce the Visual Document Retrieval Benchmark ViDoRe, composed of various page-level retrieving tasks spanning multiple domains, languages, and settings.\nThe inherent shortcomings of modern systems motivate the introduction of a new retrieval model architecture, ColPali, which leverages the document understanding capabilities of recent Vision Language Models to produce high-quality contextualized embeddings solely from images of document pages.\nCombined with a late interaction matching mechanism, ColPali largely outperforms modern document retrieval pipelines while being drastically faster and end-to-end trainable.

\n

---

\n

Contact

\n

\n
• Quentin Macé: quentin.mace@illuin.tech
\n

\n

---

\n

Citation

\n

If you use any datasets or models from this organization in your research, please cite the original dataset as follows:

\n

@misc{faysse2024colpaliefficientdocumentretrieval,\n      title={ColPali: Efficient Document Retrieval with Vision Language Models}, \n      author={Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and Céline Hudelot and Pierre Colombo},\n      year={2024},\n      eprint={2407.01449},\n      archivePrefix={arXiv},\n      primaryClass={cs.IR},\n      url={https://arxiv.org/abs/2407.01449},\n}\n\n@misc{macé2025vidorebenchmarkv2raising,\n      title={ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval}, \n      author={Quentin Macé and António Loison and Manuel Faysse},\n      year={2025},\n      eprint={2505.17166},\n      archivePrefix={arXiv},\n      primaryClass={cs.IR},\n      url={https://arxiv.org/abs/2505.17166}, \n}\n\n@misc{loison2026vidorev3comprehensiveevaluation,\n      title={ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios}, \n      author={António Loison and Quentin Macé and Antoine Edy and Victor Xing and Tom Balough and Gabriel Moreira and Bo Liu and Manuel Faysse and Céline Hudelot and Gautier Viaud},\n      year={2026},\n      eprint={2601.08620},\n      archivePrefix={arXiv},\n      primaryClass={cs.AI},\n      url={https://arxiv.org/abs/2601.08620}, \n}\n

\n

---

\n

Acknowledgments

\n

This work is partially supported by ILLUIN Technology.

\n","classNames":"hf-sanitized hf-sanitized-KPD1AzJj9WS5q5KmfJpPs"},"users":[{"_id":"60f2e021adf471cbdf8bb660","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1654090481550-60f2e021adf471cbdf8bb660.jpeg","isPro":false,"fullname":"Manuel Faysse","user":"manu","type":"user"},{"_id":"66211794ae2f58da4f00d317","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66211794ae2f58da4f00d317/kL3nsgW9ri56J0PaaSMkD.jpeg","isPro":false,"fullname":"Hugues Sibille","user":"HugSib","type":"user"},{"_id":"6264f9655f6f2e14d6ac981c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1650784534234-noauth.png","isPro":false,"fullname":"Tony Wu","user":"tonywu71","type":"user"},{"_id":"618a65e17304dc918c6602ff","avatarUrl":"/avatars/8af1112094169da80c65e24ab71c7e59.svg","isPro":false,"fullname":"Gautier Viaud","user":"gautierviaud","type":"user"},{"_id":"661e945eebe3616a1b09e279","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/661e945eebe3616a1b09e279/U3DL1BNouUpcusCKAPZm0.jpeg","isPro":false,"fullname":"Quentin Macé","user":"QuentinJG","type":"user"},{"_id":"6377b63b24d97f9f7ec70064","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6377b63b24d97f9f7ec70064/vBl68PAwwp353MOeOahMH.jpeg","isPro":false,"fullname":"Antonio Loison","user":"antonioloison","type":"user"},{"_id":"6651baf4b34bbdaec88333e7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6651baf4b34bbdaec88333e7/YTk8BiBAfgF0oDVOehULS.jpeg","isPro":false,"fullname":"Paul Teiletche","user":"paultltc","type":"user"},{"_id":"6141a88b3a0ec78603c9e784","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6141a88b3a0ec78603c9e784/DJsxSmWV39M33JFheLobC.jpeg","isPro":true,"fullname":"merve","user":"merve","type":"user"},{"_id":"66e16a677c2eb2da5109fb5c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/jPkg3g4mtCYbm8ci-ymtX.png","isPro":false,"fullname":"Antoine EDY","user":"antoineedy","type":"user"}],"userCount":9,"collections":[{"slug":"vidore/vidore-benchmark-v3-690b14a55d13035cef73e680","title":"ViDoRe Benchmark V3","description":"ViDoRe V3 is our latest benchmark, engineered to set a new industry gold standard for multi-modal, enterprise document retrieval evaluation.","gating":false,"lastUpdated":"2026-01-14T14:17:14.509Z","owner":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"items":[{"_id":"690b14b272c4efa6b29ffe97","position":1,"type":"dataset","author":"vidore","downloads":7449,"gated":false,"id":"vidore/vidore_v3_hr","lastModified":"2026-01-15T07:50:48.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":13418,"libraries":["datasets","pandas","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":9,"isLikedByUser":false,"isBenchmark":false},{"_id":"690b14b85d13035cef73e7cb","position":2,"type":"dataset","author":"vidore","downloads":7483,"gated":false,"id":"vidore/vidore_v3_finance_en","lastModified":"2026-01-15T07:49:09.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":13568,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":9,"isLikedByUser":false,"isBenchmark":false},{"_id":"690b14bea96507518487c8f7","position":3,"type":"dataset","author":"vidore","downloads":7004,"gated":false,"id":"vidore/vidore_v3_industrial","lastModified":"2026-01-15T07:50:10.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":16653,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":5,"isLikedByUser":false,"isBenchmark":false},{"_id":"690b14c4898f62bddabd2e8e","position":4,"type":"dataset","author":"vidore","downloads":6819,"gated":false,"id":"vidore/vidore_v3_pharmaceuticals","lastModified":"2026-01-15T07:53:49.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":14941,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":3,"isLikedByUser":false,"isBenchmark":false}],"position":0,"theme":"pink","private":false,"shareUrl":"https://hf.co/collections/vidore/vidore-benchmark-v3","upvotes":19,"isUpvotedByUser":false},{"slug":"vidore/vidore-community-benchmark-contributions-6960fa107e8350085b0d33f9","title":"ViDoRe Community benchmark contributions","description":"This collection regroups works done by the community to improve together Visual Retrieval !","gating":false,"lastUpdated":"2026-01-09T12:56:12.655Z","owner":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"items":[{"_id":"6960fa8535cbd2b82f6af698","position":1,"type":"dataset","author":"whybe-choi","downloads":123,"gated":false,"id":"whybe-choi/kovidore-v2-cybersecurity-beir","lastModified":"2026-01-06T07:33:12.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1725,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":1,"isLikedByUser":false,"isBenchmark":false},{"_id":"6960fa951b1a1d202839212f","position":2,"type":"dataset","author":"whybe-choi","downloads":87,"gated":false,"id":"whybe-choi/kovidore-v2-hr-beir","lastModified":"2026-01-09T14:34:34.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":3065,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"_id":"6960faa735cbd2b82f6af792","position":3,"type":"dataset","author":"whybe-choi","downloads":137,"gated":false,"id":"whybe-choi/kovidore-v2-energy-beir","lastModified":"2026-01-11T15:14:54.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2702,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"_id":"6960fac9b1464254cdcc75b6","position":4,"type":"dataset","author":"whybe-choi","downloads":106,"gated":false,"id":"whybe-choi/kovidore-v2-economic-beir","lastModified":"2026-01-06T07:33:36.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2073,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false}],"position":1,"theme":"blue","private":false,"shareUrl":"https://hf.co/collections/vidore/vidore-community-benchmark-contributions","upvotes":1,"isUpvotedByUser":false},{"slug":"vidore/vidore-benchmark-v2-67ae03e3924e85b36e7f53b0","title":"ViDoRe Benchmark v2","description":"","gating":false,"lastUpdated":"2026-01-09T12:53:43.316Z","owner":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"items":[{"_id":"67cb2712d4eaae4aca1742e6","position":6,"type":"dataset","author":"vidore","downloads":8654,"gated":false,"id":"vidore/esg_reports_v2","lastModified":"2025-07-02T13:43:09.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2912,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","tabular","text"]},"private":false,"repoType":"dataset","likes":1,"isLikedByUser":false,"isBenchmark":false},{"_id":"67cb272c15882735a4db775a","position":9,"type":"dataset","author":"vidore","downloads":8485,"gated":false,"id":"vidore/biomedical_lectures_v2","lastModified":"2025-07-02T13:43:46.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":3743,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","tabular","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"_id":"67cf0e963604a64dbce3c822","position":10,"type":"dataset","author":"vidore","downloads":8110,"gated":false,"id":"vidore/economics_reports_v2","lastModified":"2025-07-02T13:44:03.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":4317,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","tabular","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"_id":"67d424663d45ca92fec225f1","position":11,"type":"dataset","author":"vidore","downloads":7959,"gated":false,"id":"vidore/esg_reports_human_labeled_v2","lastModified":"2025-07-02T13:44:18.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1718,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","tabular","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false}],"position":3,"theme":"purple","private":false,"shareUrl":"https://hf.co/collections/vidore/vidore-benchmark-v2","upvotes":6,"isUpvotedByUser":false},{"slug":"vidore/colpali-models-673a5676abddf84949ce3180","title":"ColPali Models","description":"Pre-trained checkpoints for the ColPali model.","gating":false,"lastUpdated":"2026-01-09T12:52:35.616Z","owner":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"items":[{"_id":"67432a59de9997dd26441d86","position":0,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":0,"gated":false,"id":"vidore/colpali-v1.3-merged","availableInferenceProviders":[],"lastModified":"2025-08-04T08:50:08.000Z","likes":8,"private":false,"repoType":"model","isLikedByUser":false,"numParameters":2924613488},{"_id":"673a56824299bda07aa8f509","position":1,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":35134,"gated":false,"id":"vidore/colpali-v1.3","availableInferenceProviders":[],"lastModified":"2025-03-14T13:23:32.000Z","likes":88,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false},{"_id":"673a568679b5a48d37b6f654","position":3,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":0,"gated":false,"id":"vidore/colpali-v1.2-merged","availableInferenceProviders":[],"lastModified":"2025-02-05T19:21:59.000Z","likes":7,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false,"numParameters":2924613488},{"_id":"673a567e3c897b60a52a610d","position":4,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":22104,"gated":false,"id":"vidore/colpali-v1.2","availableInferenceProviders":[],"lastModified":"2025-03-14T13:22:48.000Z","likes":113,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false}],"position":4,"theme":"blue","private":false,"shareUrl":"https://hf.co/collections/vidore/colpali-models","upvotes":7,"isUpvotedByUser":false},{"slug":"vidore/colqwen2-models-673a56b1f31343826fc7bd26","title":"ColQwen2 Models","description":"Pre-trained checkpoints for the ColQwen2 model.","gating":false,"lastUpdated":"2026-01-09T12:52:35.622Z","owner":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"items":[{"_id":"674328779fb72af4516ae0bf","position":0,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":0,"gated":false,"id":"vidore/colqwen2-v1.0-merged","availableInferenceProviders":[],"lastModified":"2025-04-16T12:23:43.000Z","likes":19,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false,"numParameters":2209182336},{"_id":"673a56c5abddf84949ce4b0e","position":1,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":146844,"gated":false,"id":"vidore/colqwen2-v1.0","availableInferenceProviders":[],"lastModified":"2025-06-05T17:06:02.000Z","likes":115,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false},{"_id":"673a56c05d150a0c7e701651","position":2,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":0,"gated":false,"id":"vidore/colqwen2-v0.1-merged","availableInferenceProviders":[],"lastModified":"2025-03-08T23:58:02.000Z","likes":2,"private":false,"repoType":"model","isLikedByUser":false,"numParameters":2209182336},{"_id":"673a56bc53734795386ec7e4","position":3,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":104193,"gated":false,"id":"vidore/colqwen2-v0.1","availableInferenceProviders":[],"lastModified":"2025-03-21T21:44:45.000Z","likes":193,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false}],"position":5,"theme":"blue","private":false,"shareUrl":"https://hf.co/collections/vidore/colqwen2-models","upvotes":6,"isUpvotedByUser":false},{"slug":"vidore/colsmolvlm-6792418fb4267c1b39e7d7ff","title":"ColSmolVLM","description":"Pre-trained checkpoints for the ColVision models with a ColSmolVLM backbone.","gating":false,"lastUpdated":"2026-01-09T12:52:35.620Z","owner":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"items":[{"_id":"679241c3efac0ad66e1f2a53","position":0,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":600,"gated":false,"id":"vidore/colSmol-500M","availableInferenceProviders":[],"lastModified":"2025-03-14T13:19:19.000Z","likes":21,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false},{"_id":"679241cc400d620e9c796c04","position":1,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":1269,"gated":false,"id":"vidore/colSmol-256M","availableInferenceProviders":[],"lastModified":"2025-03-14T13:18:32.000Z","likes":19,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false}],"position":6,"theme":"indigo","private":false,"shareUrl":"https://hf.co/collections/vidore/colsmolvlm","upvotes":2,"isUpvotedByUser":false},{"slug":"vidore/hf-native-colvision-models-6755d68fc60a8553acaa96f7","title":"Hf-native ColVision Models","description":"Models that can be used with the native transformers 🤗 implementation instead of colpali-engine.","gating":false,"lastUpdated":"2026-01-09T12:52:35.611Z","owner":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"items":[{"_id":"67ff7cd4e31d5a3fda942bee","position":0,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":70243,"gated":false,"id":"vidore/colqwen2-v1.0-hf","availableInferenceProviders":[],"lastModified":"2025-06-02T14:51:52.000Z","likes":21,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false,"numParameters":2209182336},{"_id":"6755d6ef27f8e6a91d717672","position":1,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":2657,"gated":false,"id":"vidore/colpali-v1.3-hf","availableInferenceProviders":[],"lastModified":"2025-04-16T09:26:56.000Z","likes":26,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false},{"_id":"6755d6ea015eb159a0dd4662","position":2,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":2919,"gated":false,"id":"vidore/colpali-v1.2-hf","availableInferenceProviders":[],"lastModified":"2025-04-16T09:26:30.000Z","likes":8,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false,"numParameters":2924613488},{"_id":"68da83b22a800321226c5944","position":3,"type":"model","author":"Sahil-Kabir","authorData":{"_id":"6795abe40d9cda92655ab47f","avatarUrl":"/avatars/f3639627b84b35b18562b5ad21bdee57.svg","fullname":"Sahil Kabir","name":"Sahil-Kabir","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false},"downloads":957,"gated":false,"id":"Sahil-Kabir/colqwen2.5-v0.2-hf","availableInferenceProviders":[],"lastModified":"2025-09-13T01:43:09.000Z","likes":1,"private":false,"repoType":"model","isLikedByUser":false,"numParameters":3754885248}],"position":7,"theme":"purple","private":false,"shareUrl":"https://hf.co/collections/vidore/hf-native-colvision-models","upvotes":8,"isUpvotedByUser":false},{"slug":"vidore/vidore-benchmark-667173f98e70a1c0fa4db00d","title":"ViDoRe Benchmark","description":"Benchmark for document retrieval using visual features, introduced in the ColPali paper. Datasets are using the QA format.","gating":false,"lastUpdated":"2026-01-09T12:52:35.617Z","owner":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"items":[{"_id":"667174abaf00e07508dfd7fa","position":0,"type":"dataset","author":"vidore","downloads":426,"gated":false,"id":"vidore/arxivqa_test_subsampled","lastModified":"2025-06-20T15:48:48.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":500,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":4,"isLikedByUser":false,"isBenchmark":false},{"_id":"667174bd81b438b7c8ce263a","position":1,"type":"dataset","author":"vidore","downloads":693,"gated":false,"id":"vidore/docvqa_test_subsampled","lastModified":"2025-06-20T15:49:00.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":500,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":4,"isLikedByUser":false,"isBenchmark":false},{"_id":"667174b6a0a5d3945f8251fa","position":2,"type":"dataset","author":"vidore","downloads":366,"gated":false,"id":"vidore/infovqa_test_subsampled","lastModified":"2025-06-20T15:42:06.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":500,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":3,"isLikedByUser":false,"isBenchmark":false},{"_id":"667174c9ce36cc6c625ea07b","position":3,"type":"dataset","author":"vidore","downloads":331,"gated":false,"id":"vidore/tabfquad_test_subsampled","lastModified":"2025-06-20T15:42:42.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":280,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false}],"position":8,"theme":"orange","private":false,"shareUrl":"https://hf.co/collections/vidore/vidore-benchmark","upvotes":20,"isUpvotedByUser":false},{"slug":"vidore/vidore-benchmark-beir-672fd04012c14cc4e162f2bc","title":"ViDoRe Benchmark (BEIR)","description":"Benchmark for document retrieval using visual features, introduced in the ColPali paper. Datasets are using the BEIR format.","gating":false,"lastUpdated":"2026-01-09T12:52:35.622Z","owner":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"items":[{"_id":"67534f5fc3af453d7be3c8f8","position":0,"type":"dataset","author":"vidore","downloads":4736,"gated":false,"id":"vidore/arxivqa_test_subsampled_beir","lastModified":"2025-06-20T16:08:12.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1500,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","tabular","text"]},"private":false,"repoType":"dataset","likes":1,"isLikedByUser":false,"isBenchmark":false},{"_id":"67534f5bbbe977ea00ddec96","position":1,"type":"dataset","author":"vidore","downloads":3913,"gated":false,"id":"vidore/docvqa_test_subsampled_beir","lastModified":"2025-06-20T16:08:12.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1451,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","tabular","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"_id":"67534f623cc32b93ced629ec","position":2,"type":"dataset","author":"vidore","downloads":3210,"gated":false,"id":"vidore/infovqa_test_subsampled_beir","lastModified":"2025-06-20T16:08:13.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1494,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","tabular","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"_id":"67534f6e375fc890db18d43b","position":3,"type":"dataset","author":"vidore","downloads":3424,"gated":false,"id":"vidore/tabfquad_test_subsampled_beir","lastModified":"2025-06-20T16:08:14.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":630,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","tabular","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false}],"position":9,"theme":"orange","private":false,"shareUrl":"https://hf.co/collections/vidore/vidore-benchmark-beir","upvotes":3,"isUpvotedByUser":false},{"slug":"vidore/vidore-chunk-ocr-baseline-666acce88c294ef415548a56","title":"ViDoRe Chunk OCR (baseline)","description":"The ViDoRe benchmark was passed to Unstructured to partition each page into text chunks. Detected figures/tables were captioned with Claude 3-Sonnet.","gating":false,"lastUpdated":"2026-01-09T12:52:35.615Z","owner":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"items":[{"_id":"666ad70ae9fa3d540533b346","position":0,"type":"dataset","author":"vidore","downloads":10,"gated":false,"id":"vidore/arxivqa_test_subsampled_ocr_chunk","lastModified":"2024-06-13T10:44:24.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1436,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"_id":"666ad7139f7dd6b55ff039e8","position":1,"type":"dataset","author":"vidore","downloads":12,"gated":false,"id":"vidore/docvqa_test_subsampled_ocr_chunk","lastModified":"2024-06-13T10:53:53.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1238,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"_id":"666aec628332b10864f2672b","position":2,"type":"dataset","author":"vidore","downloads":8,"gated":false,"id":"vidore/infovqa_test_subsampled_ocr_chunk","lastModified":"2024-06-13T12:52:05.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2779,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"_id":"666accfe65a06c574504af77","position":3,"type":"dataset","author":"vidore","downloads":8,"gated":false,"id":"vidore/tabfquad_test_subsampled_ocr_chunk","lastModified":"2024-06-13T10:40:00.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":636,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false}],"position":10,"theme":"orange","private":false,"shareUrl":"https://hf.co/collections/vidore/vidore-chunk-ocr-baseline","upvotes":3,"isUpvotedByUser":false},{"slug":"vidore/colpali-paper-resources-6684070d22572e729829ce72","title":"ColPali Paper Resources","description":"Main resources for the paper: \"ColPali: Efficient Document Retrieval with Vision Language Models\"","gating":false,"lastUpdated":"2026-01-09T12:52:35.615Z","owner":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"items":[{"_id":"66840728f593a432ce60e42d","position":0,"type":"paper","id":"2407.01449","title":"ColPali: Efficient Document Retrieval with Vision Language Models","thumbnailUrl":"https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2407.01449.png","upvotes":51,"publishedAt":"2024-06-27T15:45:29.000Z","isUpvotedByUser":false},{"_id":"6684071d3780e7f96d85eb9a","position":1,"type":"model","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":7656,"gated":false,"id":"vidore/colpali","availableInferenceProviders":[],"lastModified":"2025-11-24T18:36:00.000Z","likes":474,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false},{"_id":"673079b25e6c154983d8522f","position":2,"type":"dataset","author":"vidore","downloads":2642,"gated":false,"id":"vidore/colpali_train_set","lastModified":"2025-06-20T16:07:09.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":118695,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":89,"isLikedByUser":false,"isBenchmark":false},{"_id":"6684073fa02d9851e1695759","position":3,"type":"space","author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"colorFrom":"green","colorTo":"indigo","createdAt":"2024-06-25T20:33:55.000Z","emoji":"🥇","id":"vidore/vidore-leaderboard","lastModified":"2025-12-11T09:17:52.000Z","likes":196,"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":"vidore-vidore-leaderboard.hf.space","stage":"READY"}],"sha":"06e780e831e9a21b3cd4b5650a5cb81be8b8c7f7"},"title":"Vidore Leaderboard","isLikedByUser":false,"ai_short_description":"Compare and rank visual document retrieval models across different benchmarks","ai_category":"Data Visualization","trendingScore":1,"tags":["gradio","region:us"],"featured":false}],"position":11,"theme":"green","private":false,"shareUrl":"https://hf.co/collections/vidore/colpali-paper-resources","upvotes":7,"isUpvotedByUser":false},{"slug":"vidore/vidore-page-ocr-artifact-6669de61f09324d7d940dd53","title":"ViDoRe Page OCR (artifact)","description":"ViDoRe benchmark with the full OCR text of each page. ⚠️ This dataset serves a intermediate step → use \"ViDoRe Chunk OCR (baseline)\" for evaluation!","gating":false,"lastUpdated":"2026-01-09T12:52:35.622Z","owner":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"items":[{"_id":"6669fed810c96d1566601d93","position":0,"type":"dataset","author":"vidore","downloads":17,"gated":false,"id":"vidore/arxivqa_test_subsampled_tesseract","lastModified":"2025-06-20T16:08:07.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":500,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"_id":"6669fecdd21cf7d39b216248","position":1,"type":"dataset","author":"vidore","downloads":9,"gated":false,"id":"vidore/docvqa_test_subsampled_tesseract","lastModified":"2025-06-20T16:08:05.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":500,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"_id":"6669fed63263a8feca312dc5","position":2,"type":"dataset","author":"vidore","downloads":21,"gated":false,"id":"vidore/infovqa_test_subsampled_tesseract","lastModified":"2025-06-20T16:08:07.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":500,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"_id":"6669feca45c4ec65146b6f3a","position":3,"type":"dataset","author":"vidore","downloads":8,"gated":false,"id":"vidore/tabfquad_test_subsampled_tesseract","lastModified":"2025-06-20T16:08:05.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":280,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false}],"position":14,"theme":"orange","private":false,"shareUrl":"https://hf.co/collections/vidore/vidore-page-ocr-artifact","upvotes":0,"isUpvotedByUser":false}],"datasets":[{"author":"vidore","downloads":6819,"gated":false,"id":"vidore/vidore_v3_pharmaceuticals","lastModified":"2026-01-15T07:53:49.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":14941,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":3,"isLikedByUser":false,"isBenchmark":false},{"author":"vidore","downloads":6588,"gated":false,"id":"vidore/vidore_v3_finance_fr","lastModified":"2026-01-15T07:51:24.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":13117,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":1,"isLikedByUser":false,"isBenchmark":false},{"author":"vidore","downloads":7449,"gated":false,"id":"vidore/vidore_v3_hr","lastModified":"2026-01-15T07:50:48.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":13418,"libraries":["datasets","pandas","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":9,"isLikedByUser":false,"isBenchmark":false},{"author":"vidore","downloads":7004,"gated":false,"id":"vidore/vidore_v3_industrial","lastModified":"2026-01-15T07:50:10.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":16653,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":5,"isLikedByUser":false,"isBenchmark":false},{"author":"vidore","downloads":7246,"gated":false,"id":"vidore/vidore_v3_computer_science","lastModified":"2026-01-15T07:49:20.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":8946,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":4,"isLikedByUser":false,"isBenchmark":false},{"author":"vidore","downloads":7483,"gated":false,"id":"vidore/vidore_v3_finance_en","lastModified":"2026-01-15T07:49:09.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":13568,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":9,"isLikedByUser":false,"isBenchmark":false},{"author":"vidore","downloads":1271,"gated":false,"id":"vidore/vidore_v3_energy","lastModified":"2026-01-15T07:48:10.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10732,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":2,"isLikedByUser":false,"isBenchmark":false},{"author":"vidore","downloads":6809,"gated":false,"id":"vidore/vidore_v3_physics","lastModified":"2026-01-15T07:47:59.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":16596,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["document","image","tabular","text"]},"private":false,"repoType":"dataset","likes":4,"isLikedByUser":false,"isBenchmark":false},{"author":"vidore","downloads":1427,"gated":false,"id":"vidore/vidore_v3_physics_mteb_format","lastModified":"2025-11-05T17:33:34.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":90264,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"author":"vidore","downloads":1439,"gated":false,"id":"vidore/vidore_v3_energy_mteb_format","lastModified":"2025-11-05T17:30:12.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":54906,"libraries":["datasets","dask","polars","mlcroissant"],"formats":["parquet","optimized-parquet"],"modalities":["image","text"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false}],"models":[{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":7656,"gated":false,"id":"vidore/colpali","availableInferenceProviders":[],"lastModified":"2025-11-24T18:36:00.000Z","likes":474,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false},{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":0,"gated":false,"id":"vidore/colpali-v1.3-merged","availableInferenceProviders":[],"lastModified":"2025-08-04T08:50:08.000Z","likes":8,"private":false,"repoType":"model","isLikedByUser":false,"numParameters":2924613488},{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":1807,"gated":false,"id":"vidore/colqwen-omni-v0.1","availableInferenceProviders":[],"lastModified":"2025-07-17T07:15:14.000Z","likes":93,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false},{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":0,"gated":false,"id":"vidore/bipali","availableInferenceProviders":[],"lastModified":"2025-07-15T14:54:47.000Z","likes":2,"private":false,"repoType":"model","isLikedByUser":false},{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":0,"gated":false,"id":"vidore/colqwen2.5omni-base","availableInferenceProviders":[],"lastModified":"2025-07-14T22:24:51.000Z","likes":0,"private":false,"repoType":"model","isLikedByUser":false,"numParameters":4392561792},{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":22095,"gated":false,"id":"vidore/colqwen2.5-v0.2","availableInferenceProviders":[],"lastModified":"2025-06-16T12:04:42.000Z","likes":96,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false},{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":0,"gated":false,"id":"vidore/colqwen2.5-base","availableInferenceProviders":[],"lastModified":"2025-06-06T08:59:06.000Z","likes":3,"private":false,"repoType":"model","isLikedByUser":false,"numParameters":3754885248},{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":0,"gated":false,"id":"vidore/colqwen2-base","availableInferenceProviders":[],"lastModified":"2025-06-05T17:24:53.000Z","likes":6,"private":false,"repoType":"model","isLikedByUser":false,"numParameters":2209182336},{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":146844,"gated":false,"id":"vidore/colqwen2-v1.0","availableInferenceProviders":[],"lastModified":"2025-06-05T17:06:02.000Z","likes":115,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false},{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"downloads":70243,"gated":false,"id":"vidore/colqwen2-v1.0-hf","availableInferenceProviders":[],"lastModified":"2025-06-02T14:51:52.000Z","likes":21,"pipeline_tag":"visual-document-retrieval","private":false,"repoType":"model","isLikedByUser":false,"numParameters":2209182336}],"paperPreviews":[{"id":"2601.08620","title":"ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios","thumbnailUrl":"https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08620.png"}],"spaces":[{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"colorFrom":"green","colorTo":"indigo","createdAt":"2024-06-25T20:33:55.000Z","emoji":"🥇","id":"vidore/vidore-leaderboard","lastModified":"2025-12-11T09:17:52.000Z","likes":196,"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":"vidore-vidore-leaderboard.hf.space","stage":"READY"}],"sha":"06e780e831e9a21b3cd4b5650a5cb81be8b8c7f7"},"title":"Vidore Leaderboard","isLikedByUser":false,"ai_short_description":"Compare and rank visual document retrieval models across different benchmarks","ai_category":"Data Visualization","trendingScore":1,"tags":["gradio","region:us"],"featured":false},{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"colorFrom":"yellow","colorTo":"yellow","createdAt":"2025-03-11T13:57:30.000Z","emoji":"👀","id":"vidore/visual-rag-tool","lastModified":"2025-03-21T10:08:45.000Z","likes":11,"pinned":false,"private":false,"sdk":"docker","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":"vidore-visual-rag-tool.hf.space","stage":"READY"}],"sha":"ae1680fb349b2e27c524fbfa3d5d39149c69bb7f"},"shortDescription":"Visual RAG Tool","title":"Visual Rag Tool","isLikedByUser":false,"ai_short_description":"Upload PDFs and search relevant pages","ai_category":"Document Analysis","trendingScore":0,"tags":["docker","region:us"],"featured":false},{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"colorFrom":"blue","colorTo":"blue","createdAt":"2025-03-18T09:27:15.000Z","emoji":"📚","id":"vidore/vidore-plot","lastModified":"2025-03-18T09:27:57.000Z","likes":1,"pinned":false,"private":false,"sdk":"static","repoType":"space","runtime":{"stage":"RUNNING","hardware":{"current":null,"requested":null},"storage":null,"replicas":{"requested":1,"current":1}},"title":"Vidore Plot","isLikedByUser":false,"ai_short_description":"Generate data visualizations from data sets","ai_category":"Data Visualization","trendingScore":0,"tags":["static","region:us"],"featured":false}],"buckets":[],"numBuckets":0,"numDatasets":92,"numModels":45,"numSpaces":4,"lastOrgActivities":[{"time":"2026-01-15T15:04:01.231Z","user":"QuentinJG","userAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/661e945eebe3616a1b09e279/U3DL1BNouUpcusCKAPZm0.jpeg","type":"paper","paper":{"id":"2601.08620","title":"ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios","publishedAt":"2026-01-13T15:00:33.000Z","upvotes":11,"isUpvotedByUser":true}},{"time":"2026-01-15T15:03:59.214Z","user":"antonioloison","userAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6377b63b24d97f9f7ec70064/vBl68PAwwp353MOeOahMH.jpeg","type":"paper","paper":{"id":"2601.08620","title":"ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios","publishedAt":"2026-01-13T15:00:33.000Z","upvotes":11,"isUpvotedByUser":true}},{"time":"2026-01-15T09:43:34.128Z","user":"QuentinJG","userAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/661e945eebe3616a1b09e279/U3DL1BNouUpcusCKAPZm0.jpeg","orgAvatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","type":"update","repoData":{"author":"vidore","authorData":{"_id":"66461aecbaca00c4a2bd4150","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png","fullname":"Vidore","name":"vidore","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":464,"isUserFollowing":false},"colorFrom":"indigo","colorTo":"red","createdAt":"2024-06-18T13:28:08.000Z","emoji":"👀","id":"vidore/README","lastModified":"2026-01-15T09:43:33.000Z","likes":2,"pinned":true,"private":false,"sdk":"static","repoType":"space","runtime":{"stage":"RUNNING","hardware":{"current":null,"requested":null},"storage":null,"replicas":{"requested":1,"current":1}},"title":"README","isLikedByUser":false,"trendingScore":0,"tags":["static","region:us"],"featured":false},"repoId":"vidore/README","repoType":"space","org":"vidore"}],"acceptLanguages":["*"],"canReadRepos":false,"canReadSpaces":false,"blogPosts":[],"currentRepoPage":0,"filters":{},"orgPapers":[{"paper":{"id":"2601.08620","upvotes":11,"authors":[]},"title":"ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios","publishedAt":"2026-01-13T10:00:33.000Z","thumbnail":"https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2601.08620.png","numComments":2,"upvoted":false,"submittedBy":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/661e945eebe3616a1b09e279/U3DL1BNouUpcusCKAPZm0.jpeg","name":"Quentin Macé"},"organization":{"_id":"66461aecbaca00c4a2bd4150","name":"vidore","fullname":"Vidore","avatar":"https://cdn-uploads.huggingface.co/production/uploads/66e16a677c2eb2da5109fb5c/bYfczmI-GQ-EEGbMuZUbS.png"},"isAuthorParticipating":true}],"paperView":true}">