Code Monkey home page Code Monkey logo

go-gpt-3-encoder's Introduction

go-gpt-3-encoder

Go BPE tokenizer (Encoder+Decoder) for GPT2 and GPT3.

About

GPT2 and GPT3 use byte pair encoding to turn text into a series of integers to feed into the model. This is a Go implementation of OpenAI's original Python encoder/decoder which can be found here.

This code was inspired by Javascript implementation and partially generated by OpenAI himself!

Install

go get github.com/samber/go-gpt-3-encoder

Usage

import tokenizer "github.com/samber/go-gpt-3-encoder"

encoder, err := tokenizer.NewEncoder()
if err != nil {
    log.Fatal(err)
}

str := "This is an example sentence to try encoding out on!"

encoded, err := encoder.Encode(str)
if err != nil {
    log.Fatal(err)
}

fmt.Println("We can look at each token and what it represents:")
for _, token := range encoded {
    fmt.Printf("%d -- %s\n", token, encoder.Decode([]int{token}))
}

decoded := encoder.Decode(encoded)
fmt.Printf("We can decode it back into: %s\n", decoded)

Contribute

Some corner cases are not covered by this library. See @TODO in tests.

go-gpt-3-encoder's People

Contributors

impolqris avatar munisystem avatar samber avatar seriozhakorneev avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

go-gpt-3-encoder's Issues

Package not importable

Just a heads up that this package is not importable as is.

go: github.com/samber/[email protected]: parsing go.mod:
        module declares its path as: gpt-3-encoder
                but was required as: github.com/samber/go-gpt-3-encoder

This would require changing the module name in the go.mod to be github.com/samber/go-gpt-3-encoder

Support other encodings, like `cl100k_base`

I'm making an application which calls ChatGPT API in Go, and I need to estimate how many tokens I'm using. ChatGPT uses cl100k_base encoding, while go-gpt-3-encoder only supports (I think) p50k_base.

Is there any plan to support cl100k_base?

I don't really know how BPE works, but according to this, different encodings have different vocabulary, pat regex and special tokens.

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.