Repository files navigation

Provides an implementation of today's most used tokenizers, with a focus on performance andversatility.

• Train new vocabularies and tokenize, using today's most used tokenizers.
• Extremely fast (both training and tokenization), thanks to the Rust implementation. Takesless 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 theoriginal sentence that corresponds to a given token.
• Does all the pre-processing: Truncate, Pad, add the special tokens your model needs.

Performances can vary depending on hardware, but running the~/bindings/python/benches/test_tiktoken.py should give the following on a g6 aws instance:

We provide bindings to the following languages (more to come!):

• Rust (Original implementation)
• Python
• Node.js
• Ruby (Contributed by @ankane, external repo)

You can install from source using:

pip install git+https://github.com/huggingface/tokenizers.git#subdirectory=bindings/python

our install the released versions with

pip install tokenizers

Choose your model between Byte-Pair Encoding, WordPiece or Unigram and instantiate a tokenizer:

fromtokenizersimportTokenizerfromtokenizers.modelsimportBPEtokenizer=Tokenizer(BPE())

You can customize how pre-tokenization (e.g., splitting into words) is done:

fromtokenizers.pre_tokenizersimportWhitespacetokenizer.pre_tokenizer=Whitespace()

Then training your tokenizer on a set of files just takes two lines of codes:

fromtokenizers.trainersimportBpeTrainertrainer=BpeTrainer(special_tokens=["[UNK]","[CLS]","[SEP]","[PAD]","[MASK]"])tokenizer.train(files=["wiki.train.raw","wiki.valid.raw","wiki.test.raw"],trainer=trainer)

Once your tokenizer is trained, encode any text with just one line:

output=tokenizer.encode("Hello, y'all! How are you 😁 ?")print(output.tokens)# ["Hello", ",", "y", "'", "all", "!", "How", "are", "you", "[UNK]", "?"]

Check thedocumentationor thequicktour to learn more!