{
 "id": "twinkle-ai/tw-tokenizer-bench",
 "owner": "twinkle-ai",
 "name": "tw-tokenizer-bench",
 "downloads": 9,
 "likes": 0,
 "last_modified": "2026-08-27T20:15:41.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "manual",
 "tasks": [
  "text-generation"
 ],
 "citation": "@misc{twtokenizerbench2026,\n  title = {tw-tokenizer-bench: A Traditional Chinese (Taiwan) Tokenizer Benchmark},\n  author = {Liang Hsun Huang},\n  year = {2026},\n  howpublished = {\\url{https://huggingface.co/datasets/twinkle-ai/tw-tokenizer-bench}},\n  note = {v0.1, formal register, 24,294 samples across 5 domains.}\n}",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "38de40c2d75d22f0157db6318d29658a662d52ad",
 "stated_evidence": "https://huggingface.co/datasets/twinkle-ai/tw-tokenizer-bench/blob/38de40c2d75d22f0157db6318d29658a662d52ad/README.md",
 "file_evidence": "https://huggingface.co/datasets/twinkle-ai/tw-tokenizer-bench/tree/38de40c2d75d22f0157db6318d29658a662d52ad",
 "card_nc": false
}