{
 "id": "lightonai/ArabicWeb24",
 "owner": "lightonai",
 "name": "ArabicWeb24",
 "downloads": 224,
 "likes": 24,
 "last_modified": "2024-09-23T11:40:16.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "text-generation"
 ],
 "citation": "@misc{ArabicWeb24, \ntitle={ArabicWeb24: Creating a High Quality Arabic Web-only Pre-training Dataset}, \nauthor={Farhat, May and Taghadouini, Said and Hallström, Oskar and Hajri-Gabouj, Sonja}, \norganization={LightOn, INSAT},  \nurl={www.lighton.ai/lighton-blogs/arabicweb24}, \nyear={2024}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "b2b7ba10616905fb7f91ea6d7b1c5d6a802edc14",
 "stated_evidence": "https://huggingface.co/datasets/lightonai/ArabicWeb24/blob/b2b7ba10616905fb7f91ea6d7b1c5d6a802edc14/README.md",
 "file_evidence": "https://huggingface.co/datasets/lightonai/ArabicWeb24/tree/b2b7ba10616905fb7f91ea6d7b1c5d6a802edc14",
 "card_nc": false
}