{
 "id": "r-three-moto/pre-training-data",
 "owner": "r-three-moto",
 "name": "pre-training-data",
 "downloads": 6937,
 "likes": 0,
 "last_modified": "2026-10-16T16:46:27.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@inproceedings{altintas2026moto,\n  title={{MoTo}: Mixture of Tokenizers Towards Fair Multilingual Language Modeling},\n  author={G{\\\"u}l Sena Alt{\\i}nta{\\c{s}} and Colin Raffel},\n  booktitle={The Fortieth Annual Conference on Neural Information Processing Systems},\n  year={2026},\n  url={https://openreview.net/forum?id=avjeUhPuC6}\n}\n\n@article{messmer2025multilingdatacomp,\n  title={Enhancing Multilingual LLM Pretraining with Model-Based Data Selection},\n  author={Bettina Messmer and Vinko Sabolčec and Martin Jaggi},\n  journal={arXiv},\n  year={2025},\n  url={https://arxiv.org/abs/2502.10361},\n}\n\n@misc{lozhkov2024fineweb-edu,\n  author       = { Lozhkov, Anton and Ben Allal, Loubna and von Werra, Leandro and Wolf, Thomas },\n  title        = { FineWeb-Edu: the Finest Collection of Educational Content },\n  year         = 2024,\n  url          = { https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu },\n  doi          = { 10.57967/hf/2497 },\n  publisher    = { Hugging Face }\n}\n\n@misc{penedo2024finewebdatasetsdecantingweb,\n  title={The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale},\n  author={Guilherme Penedo and Hynek Kydlíček and Loubna Ben allal and Anton Lozhkov and Margaret Mitchell and Colin Raffel and Leandro Von Werra and Thomas Wolf},\n  year={2024},\n  eprint={2406.17557},\n  archivePrefix={arXiv},\n  primaryClass={cs.CL},\n  url={https://arxiv.org/abs/2406.17557},\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "624dc7515065b269c596936802f66af27268f11d",
 "stated_evidence": "https://huggingface.co/datasets/r-three-moto/pre-training-data/blob/624dc7515065b269c596936802f66af27268f11d/README.md",
 "file_evidence": "https://huggingface.co/datasets/r-three-moto/pre-training-data/tree/624dc7515065b269c596936802f66af27268f11d",
 "card_nc": false
}