Tokenizer

Tokenizer 1.3.3

Contains Typescript and C# implementation of byte pair encoding (BPE) tokenizer for OpenAI LLMs, it is based on open sourced rust implementation in the OpenAI tiktoken.

Download for Windows

About Tokenizer

Contains Typescript and C# implementation of byte pair encoding (BPE) tokenizer for OpenAI LLMs, it is based on open sourced rust implementation in the OpenAI tiktoken.

Technical details

PublisherMicrosoft Corporation
Version1.3.3
LicenseMIT
Installer typezip
Architecturex64
Package IDMicrosoft.Tokenizer

Install Tokenizer from the command line

Install with Windows Package Manager
winget install --id=Microsoft.Tokenizer -e
Update to the latest version
winget upgrade --id=Microsoft.Tokenizer -e
Uninstall
winget uninstall --id=Microsoft.Tokenizer -e

Microsoft.ML.TokenizersMicrosoft.DeepDev.TokenizerLibtypescripttokenizationrequirescmd

Frequently asked questions

Is Tokenizer free?

Yes. Tokenizer is free and open-source software released under the MIT license.

What is the latest version of Tokenizer?

The latest version is 1.3.3.

Is it safe to download Tokenizer?

The download button links to the official installer published on github.com, the same file Windows Package Manager installs. You can verify the downloaded file by comparing its SHA-256 checksum with e0f039c6521fb7a4e3013386cd60ed64fb44ad9cab74bbe7d744b60d1afd5ce4.

Which Windows versions does Tokenizer support?

Tokenizer runs on Windows and is available for 64-bit (x64) systems.

How do I uninstall Tokenizer?

Open Settings › Apps › Installed apps, find Tokenizer and select Uninstall. From the command line, run winget uninstall --id=Microsoft.Tokenizer -e.

Is there a portable version of Tokenizer?

Yes. Tokenizer is available as a portable ZIP archive (Tokenizer.zip, 64-bit (x64)) that runs without installation. Copy it to any folder or USB drive and run it from there.