Module 12 of 16 · Master: Deep Learning & LLMs

LLMs & Transformers: The Tech Behind ChatGPT

Understand the revolutionary tech powering ChatGPT, Claude, and beyond!

30 chapters

What this module covers

This module explains the technology inside ChatGPT, Claude and similar assistants. It starts from the paper title "Attention Is All You Need" and works through self-attention, multi-head attention, positional encoding and the full transformer architecture.

Students compare BERT and GPT, then move from understanding to building: prompt engineering, fine-tuning basics, calling LLM APIs, retrieval-augmented generation (RAG), LoRA and other efficient fine-tuning methods, and finally a custom chatbot of their own.

Build neural networks, understand transformers, create with generative AI, and learn the tech behind ChatGPT.

Chapter topics

  1. Attention Is All You Need
  2. Self-Attention Mechanism
  3. Multi-Head Attention
  4. Positional Encoding
  5. Transformer Architecture
  6. BERT Explained
  7. GPT Architecture
  8. Prompt Engineering Mastery
  9. Fine-Tuning Basics
  10. LLM APIs
  11. RAG Systems
  12. LoRA & PEFT
  13. Building Custom Chatbots

Plus 17 more chapters in the app.

Activities

  • Prompt Engineering Lab
  • Build a RAG System
  • LLM API Projects

After this module, students can

  • Explain what self-attention lets a model do
  • Describe the difference between prompting, fine-tuning and RAG
  • Build a simple chatbot on top of an LLM API

Practise it with these tools

Go deeper

Start learning in the app

The first 3 chapters are free, no card needed.

Get the appSee all 16 modules