brightjonathan/BPE-Stanford

We train and implement a byte-level byte-pair encoding (BPE) tokenizer. In particular, we represent arbitrary (Unicode) strings as a sequence of bytes and train our BPE tokenizer on this byte sequence. We use this tokenizer to encode text (a string) into tokens (a sequence of integers)

11
/ 100
Experimental

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

Python

License

MIT

Category

text-tokenization-libraries

Last pushed

Aug 07, 2025

Commits (30d)

0

GitHub
Text Tokenization Libraries · 20 frameworks

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/brightjonathan/BPE-Stanford"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

SauravP97/hf-tokenizer-visualizer

Visualize HuggingFace Byte-Pair Encoding (BPE) Tokenizer encoding process

35

DePasqualeOrg/swift-tiktoken

A pure Swift implementation of OpenAI's tiktoken tokenizer

30

Usama3627/tokenizer

Implementation of BPE Tokenizer in Rust

24

andikaseptiadi/local-code-model

🛠️ Build a pure Go GPT-style transformer from scratch to grasp the fundamentals of large...

24

twinnydotdev/toxe

SentencePiece tokenizer for cross-encoders

23

Explore ML Frameworks

All categories Trending ML Framework directory Insights