Code Monkey home page Code Monkey logo

tiktoken's Introduction

Tiktoken

Openai's Tiktoken implementation written in Swift. This is basic implementation from ordinary encode/decode.

Supports vocab:

  • gpt2 (Same for gpt3)
  • r50k_base
  • p50k_base
  • p50k_edit
  • cl100k_base (gpt-4 and gpt-3.5)

And also supports asian characters and emojis.

Stars are welcome ๐Ÿ˜Š.

##ย Usage

let encoder = try await Tiktoken.shared.getEncoding("gpt-4")
let encoded = encoder?.encode(value: "้€™ๅ€‹็ฎ—ๆณ•็œŸ็š„ๅคชๆฃ’ไบ†")
print(encoded)
let decoded = encoder?.decode(value: encoded)
print(decoded)

TODO List

  • Encode native
  • Encode unstable native
  • Multithread
  • Custom vocab
  • Implements cache for loaded encoding
  • Add/Improve documentation
  • Add support for combine
  • Optimization performance
  • More testing

tiktoken's People

Contributors

aespinilla avatar grangej avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.