{
 "id": "HYUKI5/nvidia__embed-nemotron-dataset-v1",
 "owner": "HYUKI5",
 "name": "nvidia__embed-nemotron-dataset-v1",
 "downloads": 73,
 "likes": 0,
 "last_modified": "2026-11-16T12:19:03.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "nvidia/embed-nemotron-dataset-v1",
   "licence": "cc-by-sa-4.0",
   "found": true,
   "evidence": "https://huggingface.co/datasets/nvidia/embed-nemotron-dataset-v1/blob/5003f42aac552e6fc1ed4ed0f5009cf3a70d080f/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "text-retrieval",
  "text-ranking",
  "sentence-similarity",
  "text-classification"
 ],
 "citation": "@misc{babakhin2025llamaembednemotron8buniversaltextembedding,\n      title={Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Tasks}, \n      author={Yauhen Babakhin and Radek Osmulski and Ronay Ak and Gabriel Moreira and Mengyao Xu and Benedikt Schifferer and Bo Liu and Even Oldridge},\n      year={2025},\n      eprint={2511.07025},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2511.07025},",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "00e058a90d739dd31cd8a0180ac60c1a1bf81d0a",
 "stated_evidence": "https://huggingface.co/datasets/HYUKI5/nvidia__embed-nemotron-dataset-v1/blob/00e058a90d739dd31cd8a0180ac60c1a1bf81d0a/README.md",
 "file_evidence": "https://huggingface.co/datasets/HYUKI5/nvidia__embed-nemotron-dataset-v1/tree/00e058a90d739dd31cd8a0180ac60c1a1bf81d0a",
 "card_nc": false
}