Table of Contents

Overview Detailed

FM.0a About the Authors

FM.0b About This Book

FM.1 What This Book Covers & Who Should Read It

FM.1a What This Book Covers

FM.1b Who Should Read This Book

FM.3 Conventions, Callouts & Labs

FM.4 Problem-Solution Key

FM.5 Reading Pathways

FM.6 Course Syllabi

FM.7 How This Book Was Created

FM.8 The Wisdom Council

FM.9 The 42-Agent Writing Team

Part I: Foundations

Ch 00 ML & PyTorch Foundations

Ch 01 Foundations of NLP & Text Representation

Ch 02 Tokenization & Subword Models

Ch 03 Sequence Models & the Attention Mechanism

Ch 04 The Transformer Architecture

Ch 05 Decoding Strategies & Text Generation

Part II: Understanding LLMs

Ch 06 Pre-training, Scaling Laws & Data Curation

Ch 07 Modern LLM Landscape & Model Internals

Ch 08 Reasoning Models & Test-Time Compute

Ch 09 Inference Optimization & Efficient Serving

Ch 18 Interpretability & Mechanistic Understanding

Part III: Working with LLMs

Ch 10 Working with LLM APIs

Ch 11 Prompt Engineering & Advanced Techniques

Ch 12 Hybrid ML+LLM Architectures & Decision Frameworks

Part IV: Training and Adapting

Ch 13 Synthetic Data Generation & LLM Simulation

Ch 14 Fine-Tuning Fundamentals

Ch 15 Parameter-Efficient Fine-Tuning (PEFT)

Ch 16 Knowledge Distillation & Model Merging

Ch 17 Alignment: RLHF, DPO & Preference Tuning

Part V: Retrieval and Conversation

Ch 19 Embeddings, Vector Databases & Semantic Search

Ch 20 Retrieval-Augmented Generation (RAG)

Ch 21 Building Conversational AI Systems

Part VI: Agentic AI

Ch 22 AI Agent Foundations

Ch 23 Tool Use, Function Calling & Protocols

Ch 24 Multi-Agent Systems

Ch 25 Specialized Agents

Ch 26 Agent Safety, Production & Operations

Part VII: AI Applications

Ch 27 Multimodal Generation

Ch 28 LLM Applications Across Industries

Part VIII: Evaluation & Production

Ch 29 Evaluation & Experiment Design

Ch 30 Observability, Monitoring & MLOps

Ch 31 Production Engineering & Operations

Part IX: Safety & Strategy

Ch 32 Safety, Ethics & Regulation

Ch 33 LLM Strategy, Product Management & ROI

Part X: Frontiers

Ch 34 Emerging Architectures & Scaling Frontiers

Ch 35 AI, Society & Open Problems

Part XI: From Idea to AI Product

Ch 36 From Idea to Product Hypothesis

Ch 37 Building and Steering AI Products

Ch 38 Shipping and Scaling AI Products

Foundations and Setup

A Mathematical Foundations

B Machine Learning Essentials

C Python Libraries and Patterns for LLM Development

D Development Environment Setup

E Git, DVC, and Reproducibility

Reference Materials

G GPU Hardware and Cloud Compute

H Model Cards and Selection Guide

I Prompt Template Catalog

J Datasets, Benchmarks, and Leaderboards

Framework Guides

K HuggingFace: Transformers, Datasets, and Hub

L LangChain: Chains, Agents, and Retrieval

M LangGraph: Stateful Agent Workflows

N CrewAI: Multi-Agent Orchestration

O LlamaIndex: Data Indexing and Query Engines

P Semantic Kernel: Enterprise AI Orchestration

Q DSPy: Programmatic Prompt Optimization

Infrastructure and MLOps

R Experiment Tracking: W&B and MLflow

S Inference Serving: vLLM, TGI, and SGLang

T Distributed ML: PySpark, Databricks, and Ray

U Docker and Containers for LLM Deployment

Ecosystem Overview

V LLM Tooling Ecosystem