{"slug":"openlair-sentencepiece","source_name":"openlair/sentencepiece","name":"Openlair/Sentencepiece","description":"Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.","version":1,"lift":{"pass_rate_delta_pts":18.18,"pass_rate_pct":100,"total_cases":22,"passed_cases":22,"tokens_delta_pct":111,"turns_delta_pct":0,"verdict":"pass","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-07T19:56:14.137236+00:00"},"skill_score":1,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":18.18,"with_pass_pct":100,"without_pass_pct":81.8,"tokens_delta_pct":111,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"pass","never_hurt":true,"completed_at":"2026-08-07T19:56:14.137236+00:00","run_id":"a548b25f-2ac1-468a-9a01-113455f031ba","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"649f99548103987f7e315028f6480cb18f17e06eebd71768fdda75a98fd22ee3","raw_url":"https://app.decimal.ai/s/openlair-sentencepiece/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/openlair-sentencepiece"}