Giter Club home page Giter Club logo

rbertviz's Introduction

Lifecycle: maturing Travis build status AppVeyor build status Codecov test coverage

RBERTviz provides tools for convenient visualization of BERT models in the RBERT package.

Installation

You can install RBERTviz from GitHub with:

# install.packages("devtools")
devtools::install_github(
  "jonathanbratt/RBERTviz", 
  build_vignettes = TRUE
)

RBERT Installation

RBERTviz is intended to be used alongside the RBERT package. See the installation instructions in that repository.

Basic usage

RBERTviz currently enables visualization of

  1. the attention matrices for each attention head
  2. the output vectors at each transformer layer

The attention visualizer is basically a wrapper around an earlier version of the transformer visualization tools, as adapted by Jesse Vig.

Chicken Road

The output vector visualizer is a collection of routines for generating 2D PCA plots of the layer outputs, which can be interpreted as context-dependent embedding vectors.

Train

See the “Introduction to RBERTviz” vignette included with the package for more detailed examples of usage.

Disclaimer

This is not an officially supported Macmillan Learning product.

Contact information

Questions or comments should be directed to Jonathan Bratt ([email protected]) and Jon Harmon ([email protected]).

rbertviz's People

Contributors

jonathanbratt avatar jonthegeek avatar

Watchers

 avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.