cahya-wirawan/rwkv-tokenizer
A fast RWKV Tokenizer written in Rust
This tool helps developers working with RWKV language models by quickly converting plain text into numerical tokens (encoding) and vice-versa (decoding). It takes raw text in various languages and outputs sequences of numbers, which are essential for model processing, and can also reconstruct text from these numerical sequences. It's designed for developers building or integrating RWKV-based applications.
No commits in the last 6 months. Available on PyPI.
Use this if you are a developer needing a very fast and accurate tokenizer for RWKV v5+ models in Rust, Python, or WebAssembly applications.
Not ideal if you are working with other large language models (like BERT, LLaMA, or Mistral) that require a different tokenizer, or if you don't need the speed benefits of a Rust-based solution.
Stars
54
Forks
4
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Aug 12, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/cahya-wirawan/rwkv-tokenizer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AndersonBY/deepseek-tokenizer
DeepSeek Tokenizer is an efficient and lightweight tokenization library with no third-party...
dakofler/simple_tokenizers
Tokenizers is a collection of tokenization implementations focused on transparency and readability
SiriPrathikantam/custom-tokenize
A Python tokenizer project with regex, vocab building, and logging.