Skip to content
Projects

MK2112/nn-zero-to-hero-notes

View on GitHub

MK2112/nn-zero-to-hero-notes has 253 GitHub stars and 46 forks. GitHot measured 0 stars in 24 hours and 0 in 7 days. Last checked 2026-11-16 23:34 UTC. Last push 2026-11-09.

How these counts are measured

Measured star growth

in 24h
0
in 7 days
0
in 15 days
Update delayed
in 1 month
Update delayed

Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.

About

Jupyter Notebook notes on Andrej Karpathy's videos and the tutorial series, "Neural Networks: Zero to Hero."

Machine Learning

README.md

Original

Notes - Neural Networks: Zero to Hero

Andrej's GitHub Repository
Andrej's YouTube
Eureka Labs Discord

Jupyter Notebooks and Markdown files with detailed notes on Andrej Karpathy's tutorial series "Neural Networks: Zero to Hero", talks, and general audience videos. The notes provide an additional overview and documentation of the concepts and techniques covered in the videos.

Zero to Hero Tutorial Series

Video Notes
The spelled-out intro to neural networks and backpropagation: building micrograd • N001 - Building Micrograd
• Exercises
• Solved Exercises
The spelled-out intro to language modeling: building makemore • N002 - Makemore 1
• Exercises
• Solved Exercises
Building makemore Part 2: MLP • N003 - Makemore 2 - MLP
• Exercises
• Solved Exercises
Building makemore Part 3: Activations & Gradients, BatchNorm • N004 - Makemore 3 - Activations, BatchNorm
• Exercises
• Solved Exercises
Building makemore Part 4: Becoming a Backprop Ninja • N005 - Makemore 4 - Becoming a Backprop Ninja
• Exercises
• Solved Exercises
Building makemore Part 5: Building a WaveNet • N006 - Makemore 5 - WaveNet
Let's build GPT: from scratch, in code, spelled out. • N007 - GPT From Scratch
• Exercises
• Solved Exercises
Let's build the GPT Tokenizer • N008 - GPT Tokenizer
• Exercises
• Solved Exercises
Let's reproduce GPT-2 (124M) • N009 - Reproducing GPT-2

General

Video Notes
Deep Dive into LLMs like ChatGPT • G001 - Deep Dive into LLMs like ChatGPT
How I use LLMs • G002 - How I Use LLMs

Talks

Video Notes
State of GPT | BRK216HFS • T001 - State of GPT
[1hr Talk] Intro to Large Language Models • T002 - Intro to LLMs - Director's Cut
YCombinator - Andrej Karpathy: Software Is Changing (Again) • T003 - Software in the era of AI

Getting Started

  1. Clone this repository using the following command:
git clone https://github.com/MK2112/nn-zero-to-hero-notes.git
  1. Navigate to the repository, make sure to run pip install -r requirements.txt.
  2. Launch Jupyter Notebook by running this command:
jupyter notebook
  1. Within Jupyter, navigate to the repository and open the desired notebook.

The general notes and the notes on talks are written in Markdown. Markdown notes can be viewed on GitHub just the same. For the best offline Markdown experience, I recommend using Obsidian.

Contributions

Contributions are welcome and encouraged! If you find any errors, have suggestions for improvements, or want to add to the materials, please submit a pull request.

Acknowledgments

Thank you Andrej Karpathy for creating and sharing the "Neural Networks: Zero to Hero" tutorial series.
Find more of Andrej's work on his GitHub and 𝕏/Twitter.

License

MIT.
Please attribute the original content to Andrej Karpathy and provide links to the tutorial series, the videos and this repository. This repository is not affiliated with Andrej Karpathy or any of his official channels.