{
 "id": "MehTheHedgehog/TinyStories-Tiered",
 "owner": "MehTheHedgehog",
 "name": "TinyStories-Tiered",
 "downloads": 660,
 "likes": 0,
 "last_modified": "2026-09-30T13:51:27.000Z",
 "stated_licence": "cdla-sharing-1.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cdla-sharing-1.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "Original data: **Ronen Eldan and Yuanzhi Li**, authors of\n[*TinyStories: How Small Can Language Models Be and Still Speak Coherent English?*](https://arxiv.org/abs/2305.07759).\nThis dataset retains [CDLA-Sharing-1.0](https://cdla.dev/sharing-1-0/); see [LICENSE](LICENSE).\n\nModifications comprise cleaning, deduplication, deterministic selection and new split/tier organization.\nSource, attribution and modification notices are also stored in each Parquet file.",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "2068b007ca3cc349857c8996bd7de5e169635220",
 "stated_evidence": "https://huggingface.co/datasets/MehTheHedgehog/TinyStories-Tiered/blob/2068b007ca3cc349857c8996bd7de5e169635220/README.md",
 "file_evidence": "https://huggingface.co/datasets/MehTheHedgehog/TinyStories-Tiered/blob/2068b007ca3cc349857c8996bd7de5e169635220/LICENSE",
 "card_nc": false
}