MK2112 / nn-zero-to-hero-notes

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

Notes - Neural Networks: Zero to Hero

Andrej's GitHub Repository
YouTube Series

This GitHub repository contains my Jupyter Notebooks with detailed notes on Andrej Karpathy's tutorial series "Neural Networks: Zero to Hero". These notes aim to provide an additional overview of the concepts and techniques as covered in the series.

Video	Notebook
	1 - Building Micrograd
	2 - Makemore 1
	3 - Makemore 2 - MLP
	4 - Makemore 3 - Activations, BatchNorm
	5 - Makemore 4 - Becoming a Backprop Ninja
	6 - Makemore 5 - WaveNet
	7 - GPT From Scratch
	A - Talk - State of GPT
	B - Talk - Intro to LLMs - Director's Cut
	8 - GPT Tokenizer
	9 - Reproducing GPT-2

Getting Started

1. Clone this repository to your local machine using the following command:

git clone https://github.com/mk2112/nn-zero-to-hero-notes.git

2. Navigate to the repository, make sure to run pip install -r requirements.txt.
3. Launch Jupyter Notebook by running the command:

jupyter notebook

4. Within Jupyter, navigate to the repository and open the desired notebook.

Contributions

Contributions to this repository 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. Your dedication and expertise have made this resource possible. Find more of Andrej's work on his GitHub and Twitter.

License

This repository is licensed under the MIT License. Feel free to use the provided materials for educational purposes, but please attribute the original content to Andrej Karpathy and provide a link back to the tutorial series.