{
 "id": "KiteFishAI/kf-embed-pretrain-corpus-700M-raw",
 "owner": "KiteFishAI",
 "name": "kf-embed-pretrain-corpus-700M-raw",
 "downloads": 493,
 "likes": 1,
 "last_modified": "2026-04-13T14:19:48.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-retrieval",
  "sentence-similarity",
  "feature-extraction"
 ],
 "citation": "@dataset{kitefishai_kfembed_corpus_2026,\n  author       = {KiteFishAI},\n  title        = {KF-Embed Pretraining Corpus},\n  year         = {2026},\n  publisher    = {Hugging Face},\n  url          = {https://huggingface.co/datasets/KiteFishAI/kf-embed-pretrain-corpus-700M},\n  note         = {Aggregated pretraining corpus for KF-Embed multilingual embedding models. 710M (query, positive) pairs across 16 source datasets.}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "cc0cf2a2cf25b91e19e016125601cc6c4366019f",
 "stated_evidence": "https://huggingface.co/datasets/KiteFishAI/kf-embed-pretrain-corpus-700M-raw/blob/cc0cf2a2cf25b91e19e016125601cc6c4366019f/README.md",
 "file_evidence": "https://huggingface.co/datasets/KiteFishAI/kf-embed-pretrain-corpus-700M-raw/tree/cc0cf2a2cf25b91e19e016125601cc6c4366019f",
 "card_nc": false
}