This platform serves as a structured documentation hub for my journey in understanding and implementing artificial intelligence and machine learning concepts, with a primary focus on building a GPT model. The content is heavily based on Andrej Karpathy's Neural Networks: Zero to Hero series and aims to provide well-organized insights, implementations, and notes for anyone following a similar path.
This site is designed for:
-
Learners and developers interested in AI and deep learning.
-
Anyone following Karpathy's Zero to Hero series.
-
The open-source community looking for structured references and implementations.
The learning resources are divided into two primary sections: Set-1 and Set-2.
Set-1: Language Modeling Framework
| Path | Implementation of | Link |
|---|---|---|
| Backpropagation | Micrograd | Video Lecture |
| Language Model-1 | Makemore (Part 1) | Video Lecture |
| Language Model-2 | Makemore (Part 2) | Video Lecture |
| Language Model-3 | Makemore (Part 3) | Video Lecture |
| Language Model-4 | Makemore (Part 4) | Video Lecture |
| Language Model-5 | Makemore (Part 5) | Video Lecture |
Set-2: Transformer Neural Networks
| Path | Implementation of | Link |
|---|---|---|
| Transformer Model-1 (GPT) | Build GPT | Video Lecture |
| Tokenizers | Build GPT Tokenizer | Video Lecture |
| Transformer Model-2 (GPT) | Reproducing GPT-2 | Video Lecture |
Note
- This repository is a personal knowledge base for revision, experimentation, and sharing insights.
- If you find it useful, or spot any errors or improvements, feel free to reach out.
- You are welcome to reference this material for your own learning journey!
Warning
This content is based on open-source educational materials (Thanks to Andrej Karpathy). While you are encouraged to learn from and contribute to this resource, please do not copy or repurpose it for commercial use. Respect the effort behind this work, and let's continue fostering an open and ethical AI learning community!
