QuantEcon / QuantEcon/lectures

[lecture] Building a micro GPT (Blog Post)

Open
#5 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

help wanted new-lecture
Dominant language
Python
Stars
1
Forks
0
Avg merge
1h 54m
Merged PRs (30d)
3

Description

This blog post is pretty cool

https://www.towardsdeeplearning.com/andrej-karpathy-just-built-an-entire-gpt-in-243-lines-of-python-7d66cfdfa301

It builds a GPT in 243 lines of python including the autograd engine.

It learns baby names and then creates new ones.

Q: How is this different to a simple transition matrix building probabilities off of word transitions? Token size, how it builds patterns?

I think this could form the foundation of an interesting lecture using python.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the linked Towards Deep Learning article and its 243-line Python GPT example. Compare its token and pattern-building approach with the transition-matrix question, then define the lecture scope, examples, and implementation before work begins; done means an agreed lecture covering the proposed concepts.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
content, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.