microsoft

microsoft/tokenizer

Typescript and .NET implementation of BPE tokenizer for OpenAI LLMs.

C#
210
35
MIT License

This project provides TypeScript and .NET implementations of the Byte Pair Encoding (BPE) tokenizer used by OpenAI's large language models, enabling developers to tokenize prompts before sending them to LLMs. It's designed for developers working with OpenAI's APIs in Node.js or .NET environments who need to accurately calculate token usage or optimize prompt costs. The C# implementation has been superseded by `Microsoft.ML.Tokenizers`, which offers improved performance and is the recommended library for .NET developers.

Total donated
Undistributed
Share with your subscribers:

Recipients

How the donated funds are distributed

Support the dependencies

Support the repos that depend on this repository

Top contributors

shengyfu's profile
shengyfu
40 contributions
connor4312's profile
connor4312
15 contributions
sbatten's profile
sbatten
12 contributions
andreamah's profile
andreamah
8 contributions
microsoftopensource's profile
microsoftopensource
5 contributions
devm33's profile
devm33
2 contributions
ericstj's profile
ericstj
2 contributions
nt-7's profile
nt-7
2 contributions
zamoshchin's profile
zamoshchin
1 contributions
eltociear's profile
eltociear
1 contributions

Recent events

Kivach works on the Obyte network, and therefore you can track all donations.

No events yet