mirror of
https://github.com/mii443/tokenizers.git
synced 2025-08-22 16:25:30 +00:00
e4aea890d5
* Adding 2 new decoders:
- Fuse will simply concatenate all tokens into 1 string
- Strip will remove n char from left or right
Sequence(Replace("_", " "), Fuse(), Strip(1, 0)) should be what we want
for the `Metaspace` thing.
- Note: Added a new dependency from better parsing of decoders.
This is due to untagged enums which can match anything the `MustBe`
ensure there's no issue between Fuse and ByteFallback.
Since both are new the chances for backward incompatibility is low.
* Fixing picking/unpickling (using default args.).
* Stub.
* Black.
* Fixing node.
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 BPEByteLevelBPETokenizer: The byte level version of the BPESentencePieceBPETokenizer: A BPE implementation compatible with the one used by SentencePieceBertWordPieceTokenizer: The famous Bert tokenizer, using WordPiece