Code Monkey home page Code Monkey logo

neox's Introduction

Simple Annotated implementation of GPT-NeoX in PyTorch

This is a simpler implementation of GPT-NeoX in PyTorch. We have taken out several optimizations in GPT-NeoX for simplicity.

Annotated implementation

Screenshot of annotated implementation

Sample usages

Playground

Screenshot of playground

Evaluation

Task Metric NeoX Impl (2 GPU) This repo (1 GPU)
anli_r1 acc 0.3270 0.3360
acc_stderr 0.0148 0.0149
anli_r2 acc 0.3410 0.3350
acc_stderr 0.0150 0.0149
anli_r3 acc 0.3567 0.3525
acc_stderr 0.0138 0.0149
hellaswag acc 0.5351 0.5353
acc_stderr 0.0050 0.0050
acc_norm 0.7140 0.7145
acc_norm_stderr 0.0045 0.0045
lambada acc 0.7211 0.7204
acc_stderr 0.0062 0.0063
ppl 3.6760 3.6375
ppl_stderr 0.0760 0.0747
piqa acc 0.7748 0.7758
acc_stderr 0.0097 0.0097
acc_norm 0.7786 0.7845
acc_norm_stderr 0.0097 0.0096
winogrande acc 0.6598 0.6582
acc_stderr 0.0133 0.0133
wsc acc 0.5096 0.5000
acc_stderr 0.0493 0.0493

neox's People

Contributors

vpj 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.