{
 "id": "orionweller/mmBERT-pretraining-data-chunk3",
 "owner": "orionweller",
 "name": "mmBERT-pretraining-data-chunk3",
 "downloads": 1673,
 "likes": 0,
 "last_modified": "2025-09-09T03:56:53.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "fill-mask"
 ],
 "citation": "@misc{marone2025mmbertmodernmultilingualencoder,\n      title={mmBERT: A Modern Multilingual Encoder with Annealed Language Learning}, \n      author={Marc Marone and Orion Weller and William Fleshman and Eugene Yang and Dawn Lawrie and Benjamin Van Durme},\n      year={2025},\n      eprint={2509.06888},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2509.06888}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "92ef7aa74b589336c085a0c09d6741045105ad3f",
 "stated_evidence": "https://huggingface.co/datasets/orionweller/mmBERT-pretraining-data-chunk3/blob/92ef7aa74b589336c085a0c09d6741045105ad3f/README.md",
 "file_evidence": "https://huggingface.co/datasets/orionweller/mmBERT-pretraining-data-chunk3/tree/92ef7aa74b589336c085a0c09d6741045105ad3f",
 "card_nc": false
}