Skip to content
中文

Leaderboard / Science

huggingface-tokenizers

huggingface-tokenizers (Orchestra-Research/AI-Research-SKILLs): Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Stars
13k
Votes
—
Score
41.2863

Source: Orchestra-Research/AI-Research-SKILLs · 02-tokenization/huggingface-tokenizers/SKILL.md

Open ↗
npx skills add Orchestra-Research/AI-Research-SKILLs --skill huggingface-tokenizers

Rate this skill

Related skills

01 axolotlOrchestra-Research/AI-Research-SKILLs Science 13k
4128.6
↗
02 neuroskill-bciNousResearch/hermes-agent Science 255k
5406.3
↗
03 aeonK-Dense-AI/scientific-agent-skills Science 52k
4720.1
↗
04 anndataK-Dense-AI/scientific-agent-skills Science 52k
4720.1
↗
05 powerbi-modelinggithub/awesome-copilot Science 40k
4603.6
↗