huggingface-tokenizers

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-perf

By davila7 · 347 installs

npx skills add davila7/claude-code-templates --skill huggingface-tokenizers

Source repository · Upstream listing