{
 "id": "lightonai/embeddings-pre-training-curated",
 "owner": "lightonai",
 "name": "embeddings-pre-training-curated",
 "downloads": 13079,
 "likes": 16,
 "last_modified": "2026-08-27T10:20:32.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@misc{sourty2025denseonlateon,\n  title={DenseOn with LateOn: Open State-of-the-Art Single and Multi-Vector Models},\n  author={Sourty, Raphael and Chaffin, Antoine and Weller, Orion and Demoura, Paulo and Chatelain, Am\u00e9lie},\n  year={2026},\n  howpublished={\\url{https://huggingface.co/blog/lightonai/denseon-lateon}},\n}\n\n@article{zhang2024mgte,\n  title={mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval},\n  author={Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Wen and Dai, Ziqi and Tang, Jialong and Lin, Huan and Yang, Baosong and Xie, Pengjun and Huang, Fei and Zhang, Meishan and Li, Wenjie and Zhang, Min},\n  journal={arXiv preprint arXiv:2407.19669},\n  year={2024}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "1bdc6433cfa9de28d3816e0550b1cb3107ffd92d",
 "stated_evidence": "https://huggingface.co/datasets/lightonai/embeddings-pre-training-curated/blob/1bdc6433cfa9de28d3816e0550b1cb3107ffd92d/README.md",
 "file_evidence": "https://huggingface.co/datasets/lightonai/embeddings-pre-training-curated/tree/1bdc6433cfa9de28d3816e0550b1cb3107ffd92d",
 "card_nc": false
}