AndersonBY/deepseek-tokenizer

DeepSeek Tokenizer is an efficient and lightweight tokenization library with no third-party runtime dependencies, making it a streamlined and efficient choice for tokenization tasks.

49
/ 100
Emerging

This library helps developers convert human-readable text into numerical tokens that artificial intelligence models can understand and process. You input a string of text, and it outputs a list of corresponding token IDs. This is used by AI developers and machine learning engineers who are preparing text data for training or inference with large language models.

Available on PyPI.

Use this if you are a developer working with AI models and need a fast, lightweight way to tokenize text without adding many other software dependencies to your project.

Not ideal if you are an end-user looking for a tool to analyze text or generate content, as this is a technical component for building AI systems.

AI-development natural-language-processing machine-learning-engineering text-pre-processing language-model-preparation
No License No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 17 / 25
Community 14 / 25

How are scores calculated?

Stars

42

Forks

7

Language

Python

License

Last pushed

Feb 19, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/AndersonBY/deepseek-tokenizer"

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