GenAI Foundations

Master the core concepts and practical essentials of Generative AI and Large Language Models

Welcome to the Generative AI Foundations module. This module provides a comprehensive introduction to Large Language Models (LLMs), covering how they are built, how they work conceptually, and how to start building applications with them.

🗺️ Module Overview

This module is designed to bridge the gap between AI theory and software development:

📚 Module Curriculum & Roadmap

Explore the sections in this module using the cards below:

1. From AI to Generative AI

Learn the historical shift from rule-based expert systems to statistical machine learning, deep learning, NLP sequential models, and the transformer/attention revolution.

2. The Transformer Model

Compare encoder-only, decoder-only, and seq-to-seq models. Explore key components like embeddings, positional encodings, and self-attention mechanisms.

3. How LLMs Work

Understand tokens and tokenizers, context window constraints, LLM lifecycle (pre-training, fine-tuning, RLHF/DPO), and model hosting architectures (local, proprietary, open-weight).

4. Using LLMs in Real Apps

Review input/output token pricing, model selection strategies, types of applications built with LLMs, and the modern GenAI application stack.