Understanding Large Language Models (LLMs)
Course Curriculum
13 modules designed to master the subject.
Module 1: What Are Large Language Models?
Foundations of LLMs, how they differ from traditional software, and real-world uses.
Module 1 Lesson 1: Defining Large Language Models
Welcome to the first lesson of the LLM course! We start by defining what Large Language Models actually are, why they are 'large', and what they can (and cannot) do.
Module 1 Lesson 2: How LLMs Differ from Traditional Software
In this lesson, we explore the fundamental shift in computing: moving from rigid 'If-Then' logic to the fluid, probabilistic nature of Large Language Models.
Module 1 Lesson 3: Real-World Uses of LLMs
In our final lesson of Module 1, we look at where LLMs are actually being used to create value, from search and coding to decision support systems.
Module 2: From Text to Tokens
Tokenization, context windows, and why computers need numerical representations of text.
Module 2 Lesson 1: Why Computers Cannot Understand Text Directly
Before we learn about tokens, we must understand the fundamental gap between how humans see text and how computers process data: the Numerical Gap.
Module 2 Lesson 2: Tokenization – The Vocabulary of AI
How do LLMs actually 'read'? They don't see words; they see tokens. Learn the secrets of subword tokenization and why it's the secret sauce of modern AI.
Module 2 Lesson 3: Token Limits and Context Windows
Why does the AI forget what you said 20 minutes ago? In our final lesson of Module 2, we explore the 'Context Window' and the hard limits of model memory.
Module 3: Embeddings – Meaning as Numbers
Semantic vector space, how embeddings are learned, and their use in RAG and search.
Module 3 Lesson 1: What Embeddings Are
How does a computer know that a 'King' is like a 'Queen' but not like a 'Kilometer'? In this lesson, we explore Embeddings: the mathematical heart of AI meaning.
Module 3 Lesson 2: How Embeddings Are Learned
Embeddings aren't created by humans; they are learned by machines. In this lesson, we look at the intuition behind how LLMs build their conceptual map of the world.
Module 3 Lesson 3: Embeddings in Practice
How are businesses actually using those big lists of numbers? In our final lesson of Module 3, we look at semantic search, RECOMMENDATIONS, and the basics of RAG.
Module 4: Training a Language Model
Pretraining, fine-tuning, alignment (RLHF), and the objective of next-token prediction.
Module 4 Lesson 1: The Core Objective – Next Token Prediction
Why does predicting the next word lead to human-like intelligence? In this lesson, we explore the simple mathematical goal that drives trillions of parameters.
Module 4 Lesson 2: Training Data – The Fuel of AI
Where do LLMs get their knowledge? In this lesson, we explore the datasets that power models, the importance of data deduplication, and the risk of 'Data Contamination'.
Module 4 Lesson 3: Pretraining vs Fine-Tuning
An LLM isn't 'born' knowing how to be a helpful assistant. It goes through two distinct life stages: Pretraining and Fine-Tuning. Learn why both are critical.
Module 4 Lesson 4: Loss Functions – Measuring Mistakes
How does a model actually 'know' it's getting better? In our final lesson of Module 4, we explore the conceptual magic of the Loss Function.
Module 5: The Transformer Architecture
Attention mechanisms, layers, and why Transformers revolutionized NLP.
Module 5 Lesson 1: Why Transformers Replaced Earlier Models
Before-Transformer (B.T.) and After-Transformer (A.T.). In this lesson, we learn about the architectural breakthrough that allowed AI to finally understand context at scale.
Module 5 Lesson 2: Attention Mechanism (Intuitive Explanation)
Why is 'Self-Attention' the most important invention in AI history? In this lesson, we use a simple library analogy to explain how LLMs decide what to focus on.
Module 5 Lesson 3: Layers and Depth
Why does an LLM need 96 layers? In this lesson, we explore how stacking attention blocks creates a hierarchy of meaning, moving from basic letters to complex abstract logic.
Module 5 Lesson 4: Positional Encoding – The Sense of Order
Transformers see a sentence all at once, which means they are naturally blind to word order. In our final lesson of Module 5, we learn how AI adds the 'GPS of words' to stay organized.
Module 6: Inference – How LLMs Generate Text
Decoding strategies, temperature, top-p/top-k sampling, and output variation.
Module 6 Lesson 1: From Prompt to Output
How does a set of math formulas actually write a story? In this lesson, we look at the 'Inference' phase—the step-by-step process of turning a prompt into a response.
Module 6 Lesson 2: Sampling Strategies
Why does an LLM give different answers to the same question? In this lesson, we learn about Temperature, Top-k, and Top-p—the knobs we use to control AI creativity.
Module 6 Lesson 3: Why Outputs Change
Why does the AI say things differently every time? In our final lesson of Module 6, we look at the trade-offs between Determinism and Creativity in model responses.
Module 7: Why LLMs Hallucinate
The probabilistic nature of hallucinations and strategies to mitigate them.
Module 7 Lesson 1: What Hallucinations Are
Why does an AI sometimes lie with total confidence? In this lesson, we define 'Hallucinations' and learn to identify the difference between a creative slip and a factual failure.
Module 7 Lesson 2: Causes of Hallucinations
Why does it happen? Is it a data gap or a logic failure? In this lesson, we break down the three primary causes of LLM hallucinations: Gaps, Blur, and Eagerness.
Module 7 Lesson 3: Detecting Hallucinations
How can you tell if an AI is lying? In this lesson, we learn about Logprobs, Self-Consistency checks, and the 'Stochastic Signature' of a hallucination.
Module 7 Lesson 4: Reducing Hallucinations
How can we make AI reliable enough for a bank or a hospital? In our final lesson of Module 7, we explore the industry best practices for silencing the 'LIAR' in the machine.
Module 8: Bias, Safety, and Alignment
Training data bias, alignment techniques (Constitutional AI), and safety tradeoffs.
Module 8 Lesson 1: What Is Bias in LLMs?
LLMs don't have their own opinions, but they do reflect ours. In this lesson, we explore how bias enters the machine and why 'Neutrality' is harder than it sounds.
Module 8 Lesson 2: Safety Filters and Guardrails
How does the AI know when to say 'No'? In this lesson, we look at the invisible police force of AI—Safety Filters and Guardrails—that prevent harm while sometimes causing frustration.
Module 8 Lesson 3: The Alignment Problem
What happens when an AI is 'too good' at its job? In our final lesson of Module 8, we explore the Alignment Problem: the struggle to ensure AI goals match human values.
Module 9: Fine-Tuning and Customization
Domain adaptation, LoRA, and when to choose fine-tuning over prompting.
Module 9 Lesson 1: Why Fine-Tune?
General-purpose LLMs are good for many things, but sometimes you need a specialist. In this lesson, we explore the reasons to fine-tune your own version of an LLM.
Module 9 Lesson 2: Full Fine-Tuning vs. PEFT
How do you customize a 70-billion parameter model on a single GPU? In this lesson, we learn about LoRA and PEFT—the breakthroughs that democratized AI fine-tuning.
Module 9 Lesson 3: Datasets for Fine-Tuning
How much data do you really need to teach an AI a new trick? In our final lesson of Module 9, we learn about the 'Less is More' philosophy of fine-tuning datasets.
Module 10: LLMs in Applications
RAG, function calling, agents, and multi-step reasoning.
Module 10 Lesson 1: Prompt Engineering Mastery
How you ask matters just as much as what you ask. In this lesson, we learn the technical art of Prompt Engineering: from Zero-Shot to Chain-of-Thought.
Module 10 Lesson 2: Connecting to Tools (Function Calling)
LLMs are smart, but they can't browse the web or calculate math perfectly by themselves. In this lesson, we learn about Function Calling—how LLMs use external tools to get the job done.
Module 10 Lesson 3: Creating a Simple Workflow
How do you go from a prompt to a real app? In our final lesson of Module 10, we learn how to link RAG, Tools, and Memory into a single cohesive AI Agent.
Module 11: Limitations of LLMs
Lack of true understanding, brittleness, and environmental impact.
Module 11 Lesson 1: The Reasoning Gap (System 1 vs System 2)
Is an LLM actually 'thinking'? In this lesson, we explore the Reasoning Gap using the System 1 vs System 2 framework to understand why AI fails at simple logic while mastering complex prose.
Module 11 Lesson 2: Correlation vs. Causation
AI knows what follows what, but does it know why? In this lesson, we learn why LLMs are 'Statistical Parrots' when it comes to cause and effect.
Module 11 Lesson 3: Long-Horizon Planning
Why does the AI forget its original goal halfway through a task? In our final lesson of Module 11, we explore 'Long-Horizon Planning' and the limits of AI persistence.
Module 12: The Future of Large Language Models
Multimodal systems, autonomous agents, and new efficient architectures.
Module 12 Lesson 1: Multimodality (Beyond Text)
Language is only the beginning. In this lesson, we explore Multimodality—the shift from Large Language Models to Large Multimodal Models that can see, hear, and speak.
Module 12 Lesson 2: Personalization and Memory
In the past, AI forgot your name as soon as the session ended. In this lesson, we look at the future of Persistent Memory and the rise of your 'Digital Twin'.
Module 12 Lesson 3: The Path to AGI
Are LLMs the end of the road, or just the beginning? In our final lesson of the core curriculum, we explore Artificial General Intelligence (AGI) and the future of human-AI partnership.
Capstone Project
Applying concepts to explain LLMs to a non-technical audience with visual aids.
Course Overview
Format
Self-paced reading
Duration
Approx 6-8 hours
Found this course useful? Support the creator to help keep it free for everyone.
Support the Creator