Miss any of our Open RFC calls?Watch the recordings here! »

tokenizers

0.7.0 • Public • Published



Build GitHub


NodeJS implementation of today's most used tokenizers, with a focus on performance and versatility. Bindings over the Rust implementation. If you are interested in the High-level design, you can go check it there.

Main features

  • Train new vocabularies and tokenize using 4 pre-made tokenizers (Bert WordPiece and the 3 most common BPE versions).
  • Extremely fast (both training and tokenization), thanks to the Rust implementation. Takes less than 20 seconds to tokenize a GB of text on a server's CPU.
  • Easy to use, but also extremely versatile.
  • Designed for research and production.
  • Normalization comes with alignments tracking. It's always possible to get the part of the original sentence that corresponds to a given token.
  • Does all the pre-processing: Truncate, Pad, add the special tokens your model needs.

Installation

npm install tokenizers@latest

Basic example

import { BertWordPieceTokenizer } from "tokenizers";
 
const wordPieceTokenizer = await BertWordPieceTokenizer.fromOptions({ vocabFile: "./vocab.txt" });
const wpEncoded = await wordPieceTokenizer.encode("Who is John?", "John is a teacher");
 
console.log(wpEncoded.length);
console.log(wpEncoded.tokens);
console.log(wpEncoded.ids);
console.log(wpEncoded.attentionMask);
console.log(wpEncoded.offsets);
console.log(wpEncoded.overflowing);
console.log(wpEncoded.specialTokensMask);
console.log(wpEncoded.typeIds);
console.log(wpEncoded.wordIndexes);

Provided Tokenizers

  • BPETokenizer: The original BPE
  • ByteLevelBPETokenizer: The byte level version of the BPE
  • SentencePieceBPETokenizer: A BPE implementation compatible with the one used by SentencePiece
  • BertWordPieceTokenizer: The famous Bert tokenizer, using WordPiece

License

Apache License 2.0

Keywords

none

Install

npm i tokenizers

DownloadsWeekly Downloads

114

Version

0.7.0

License

Apache-2.0

Unpacked Size

94.2 kB

Total Files

39

Last publish

Collaborators

  • avatar
  • avatar
  • avatar