{
 "id": "allenai/tulu-2.5-preference-data",
 "owner": "allenai",
 "name": "tulu-2.5-preference-data",
 "downloads": 535,
 "likes": 18,
 "last_modified": "2024-07-22T01:35:43.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "reinforcement-learning"
 ],
 "citation": "@misc{ivison2024unpacking,\n      title={{Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback}}, \n      author={{Hamish Ivison and Yizhong Wang and Jiacheng Liu and Ellen Wu and Valentina Pyatkin and Nathan Lambert and Yejin Choi and Noah A. Smith and Hannaneh Hajishirzi}}\n      year={2024},\n      eprint={2406.09279},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "6e87e7ba11eeb2a21db459cf13267f62d1feea23",
 "stated_evidence": "https://huggingface.co/datasets/allenai/tulu-2.5-preference-data/blob/6e87e7ba11eeb2a21db459cf13267f62d1feea23/README.md",
 "file_evidence": "https://huggingface.co/datasets/allenai/tulu-2.5-preference-data/tree/6e87e7ba11eeb2a21db459cf13267f62d1feea23",
 "card_nc": false
}