npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2024 – Pkg Stats / Ryan Hefner

@microsoft/tiktokenizer

v1.0.9

Published

Tokenizer for OpenAI large language models.

Downloads

29,310

Readme

Tokenizer

This is a Typescript implementation of byte pair encoding(BPE) tokenizer for OpenAI LLMs, it's based on open sourced rust implementation in the OpenAI tiktoken. It's valuable to run prompt tokenization in Nodejs or web browser before feeding prompt into a LLM.

How to use

The npm package @microsoft/tiktokenizer is published in NPMJS Packages Registry. Install the npm package in your project:

npm install @microsoft/tiktokenizer

Example Typescript code to use @microsoft/tiktokenizer in your code:

import {
    createByModelName
  } from '@microsoft/tiktokenizer';

const IM_START = "<|im_start|>";
const IM_END = "<|im_end|>";
const specialTokens: ReadonlyMap<string, number> = new Map([
  [IM_START, 100264],
  [IM_END, 100265],
]);

const str = "<|im_start|>Hello World<|im_end|>";
let tokenizer = null;
const createTokenizer = async () => {
    tokenizer = await createByModelName("gpt-3.5-turbo", specialTokens);
    var out1 = tokenizer.encode(str, Array.from(specialTokens.keys()));
    console.log(out1);
    var out2 = tokenizer.encodeTrimSuffix(str, 3, Array.from(specialTokens.keys()));
    console.log(out2.tokenIds);
    console.log(out2.text);
    var out3 = tokenizer.encodeTrimPrefix(str, 3, Array.from(specialTokens.keys()));
    console.log(out3.tokenIds);
    console.log(out3.text);
}
createTokenizer();

In production setting, you should pre-download the BPE rank file and call createTokenizer API to avoid downloading the BPE rank file on the fly. You can find the model to encoder and encoder to BPE rank file link mapping in: tokenizerBuilder.ts.

Contributing

We welcome contributions. Please follow this guideline.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.