{
 "id": "Kiy-K/pretraining-corpus",
 "owner": "Kiy-K",
 "name": "pretraining-corpus",
 "downloads": 51,
 "likes": 3,
 "last_modified": "2025-12-05T01:34:24.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@dataset{kiy_k_2025_pretraining_corpus,\n  author       = {Khoi K.},\n  title        = {Kiy-K Synthetic Pretraining Corpus},\n  year         = {2025},\n  publisher    = {Hugging Face},\n  url          = {https://huggingface.co/datasets/Kiy-K/pretraining-corpus}\n}- text-generation\nlanguage:\n- en\n---",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "71a289d1b1e0b4e3e52f0357e95ed8af80468729",
 "stated_evidence": "https://huggingface.co/datasets/Kiy-K/pretraining-corpus/blob/71a289d1b1e0b4e3e52f0357e95ed8af80468729/README.md",
 "file_evidence": "https://huggingface.co/datasets/Kiy-K/pretraining-corpus/tree/71a289d1b1e0b4e3e52f0357e95ed8af80468729",
 "card_nc": false
}