🧠 GenAI for Data Scientists [Migration Pending]

This repo is a practical, structured guide for data scientists transitioning into Generative AI — built from scratch to go from traditional ML to deploying GenAI applications.

🎯 Who is this for?

If you're familiar with machine learning and want to ramp up on GenAI without getting lost in research papers, this is for you.

🧪 Purpose

This is not a polished course or GenAI hype repo. It's a deliberate, hands-on learning path. The goal: arrive at practical readiness to work with modern GenAI stacks — from Nueral Network fundamentals to real genAI app deployments.

🧱 Learning Flow

Each notebook is self-contained and builds on the prior:

1. Neural Networks – Foundations of neural networks
2. Deep Learning – Concepts like depth, activations, backprop
3. Transformers Architecture – The core building block of LLMs
4. Large Language Models – What makes a model an LLM
5. Prompt Engineering – How to use models effectively
6. Fine Tuning LLMs – When and how to fine-tune
7. Huggingface Workflows – Real-world tooling and workflows
8. GenAI Use Cases – Common applied patterns (Q&A, summarization, etc.)
9. Deploying GenAI Models – Serve your own GenAI-powered apps

---