Coder Social home page Coder Social logo

alextmjugador / redwoodresearch-interp-docker Goto Github PK

View Code? Open in Web Editor NEW
0.0 1.0 0.0 6 KB

๐Ÿ“ฆ Redwood Research's transformer interpretability tools, conveniently packaged in a Docker container for simple and reproducible deployments.

License: MIT License

Dockerfile 92.05% Shell 7.95%
ai ai-safety docker ai-interpretability redwood-research

redwoodresearch-interp-docker's Introduction

redwoodresearch-interp-docker logo

redwoodresearch-interp-docker

Redwood Research's transformer interpretability tools, conveniently packaged in a Docker container for simple and reproducible deployments.

This repository provides a simple Dockerfile defining an image containing a clean, functioning installation of Redwood Research's transformer interpretability tools. Setting up these tools across different environments can be challenging due to numerous assumptions about the running environment, but this Docker image simplifies that process.

The build.sh script facilitated the upload of the image to the GitHub Packages container registry, where a prebuilt version of the defined Docker image is stored.

โœจ Getting started

The quickest way to utilize this Docker image is by pulling it from the GitHub Packages container registry. Before pulling the image, ensure that your Docker daemon is authenticated to the GitHub Packages container registry. The following commands perform this authentication and start a throwaway container with the image:

$ docker login ghcr.io -u <your GitHub user>
$ docker run -it --rm --gpus all -p 3000:3000 -p 6789:6789 ghcr.io/alextmjugador/redwoodresearch-interp

If everything goes smoothly, running the above commands will launch the interpretability web UI on port 3000. The interpretability tools were not modified, so all details regarding how they function apply to this Docker container. Enjoy your interpretability session!

redwoodresearch-interp-docker's People

Contributors

alextmjugador avatar

Watchers

 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.