Skip to content

Drivel GPT: The Nonsense Generating Language Model

Notifications You must be signed in to change notification settings

jmarkowski/drivel-gpt

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

42 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Drivel GPT

This codebase contains a simple, custom version of a language model using a Generative Pretrained Transformer (GPT) model, created by following along Andrej Karpathy's Let's build GPT: from scratch, in code, spelled out., which models its implementation after the landmark paper on transformers, namely Attention is All You Need.

The output generated by this GPT model will depend on the dataset that it's trained on, and often times, will just be gibberish. Hence, the name :)

Purpose

To understand and appreciate how a GPT model works under the hood.

Sample Output

QUEEN:
Thou wranst I am dear with'd, in like a speak;
The dring wife-hear'd unstrard, whet hereing with
where broud them; menny our wringled canspess;
for here with like her cheep? Gremion, my solurand,
Good lord, a truip gateny and you.

DUKE VINCENTIO:
But by oyid miney rey, was that I no, 'That with lown'd
Deling I disacious nursed spakes on nurbland sts.

POMPEYON:
And, by The warm, lord! darchs'-moth and i

Installation

Install Conda

curl -O https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-arm64.sh

sh Miniconda3-latest-MacOSX-arm64.sh

Install pytorch

conda install pytorch=1.13.1 -c pytorch

Resources

Videos

Papers

Repositories

Articles & Media

About

Drivel GPT: The Nonsense Generating Language Model

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages