{
 "id": "lightonai/LightOnOCR-mix-0126",
 "owner": "lightonai",
 "name": "LightOnOCR-mix-0126",
 "downloads": 1438,
 "likes": 114,
 "last_modified": "2026-01-26T16:29:46.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-to-text"
 ],
 "citation": "@misc{lightonocr2_2026,\n  title        = {LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR},\n  author       = {Said Taghadouini and Adrien Cavaill\\`{e}s and Baptiste Aubertin},\n  year         = {2026},\n  howpublished = {\\url{https://arxiv.org/pdf/2601.14251}}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "af0218b88fc337468d91f9c107ae33453f65cf30",
 "stated_evidence": "https://huggingface.co/datasets/lightonai/LightOnOCR-mix-0126/blob/af0218b88fc337468d91f9c107ae33453f65cf30/README.md",
 "file_evidence": "https://huggingface.co/datasets/lightonai/LightOnOCR-mix-0126/tree/af0218b88fc337468d91f9c107ae33453f65cf30",
 "card_nc": false
}