LVL1
0 Total XP0 / 100 XP to Lvl 2
1 Day Streak
55-Lesson Mastery Track

LLM Curriculum: 7 Levels of Mastery

From foundational principles to subword tokens, multi-head attention, backpropagation, LoRA, and agentic architectures. Each lesson features interactive check quizzes and direct links to simulation sandboxes.

Level 1 — Foundations

0 / 5 Completed

Core concepts, architectures, training vs inference, and scaling laws.

#1

What Is an LLM?

Understand what a Large Language Model actually is, how it processes sequences, and why it is fundamentally an autoregressive token predictor.

#2

What Makes an LLM Large?

Explore the three dimensions of scale: parameters, dataset volume (tokens), and compute (FLOPs).

#3

AI vs ML vs Deep Learning vs LLM

Disentangle the hierarchy of Artificial Intelligence, Machine Learning, Deep Learning, and Large Language Models.

#4

Training vs Inference

Understand the fundamental divide between the compute-heavy training phase and the generation-focused inference phase.

#5

Parameters vs Hyperparameters

Learn the distinction between parameters learned by the model and hyperparameters set by researchers.

Level 2 — Text & Representations

0 / 5 Completed

From human characters to subwords, token IDs, vocabularies, and vector embeddings.

#6

What Is Tokenization?

Learn how neural networks convert unstructured text strings into discrete subword integer tokens.

#7

Tokens vs Words

Understand the rule of thumb for token-to-word ratios and why code and non-English text consume more tokens.

#8

Token IDs and Vocabulary

Follow the conversion from string tokens to their integer IDs in the model vocabulary table.

#9

Vocabulary Design & Trade-offs

Learn why vocabulary size is a critical architectural trade-off between sequence length and parameter memory.

#10

Vector Embeddings: Meaning in High Dimensions

Discover how integer token IDs are transformed into continuous vector embeddings that capture semantic relationships.

Level 3 — Transformers & Attention

0 / 10 Completed

Self-attention, Query-Key-Value mechanics, multi-head projection, and residual blocks.

#11

Why Transformers? (The Breakthrough of 2017)

Learn why the 2017 paper "Attention Is All You Need" replaced Recurrent Neural Networks (RNNs) and LSTMs.

#12

Positional Information: Why Order Matters

Understand how transformers inject word order information using sinusoidal encodings or Rotary Position Embeddings (RoPE).

#13

Self-Attention: The Engine of Context

Visualize how each token in a sentence looks at all other tokens to update its own contextual representation.

#14

Query, Key, Value (Q, K, V) Explained

Understand the database retrieval analogy: Query = what I am looking for, Key = what I offer, Value = the actual content.

#15

Attention Scores and Scaling

Follow the math behind the scaled dot-product attention equation step by step.

#16

Multi-Head Attention: Multiple Perspectives

Discover why models split attention into multiple parallel heads to track grammar, facts, and co-references simultaneously.

#17

Feed-Forward Networks (FFN): The Knowledge Store

Learn how multi-layer perceptron blocks inside transformer layers store factual associations.

#18

Residual Connections: Enabling Deep Networks

Understand how skip connections (Add & Norm) allow gradients to flow unimpeded through hundreds of layers.

#19

Layer Normalization & RMSNorm

Discover how normalizing activation scales keeps numerical stability during billion-parameter training.

#20

The Complete Transformer Decoder Block

Assemble all pieces: RMSNorm, Multi-Head Attention, Residuals, FFN, and Output Projections.

Level 4 — Generation & Sampling

0 / 8 Completed

Logits, Softmax normalization, temperature scaling, Top-K, Top-P, and autoregression.

#21

Logits: Raw Unnormalized Scores

Understand the unnormalized real numbers produced by the model before probability conversion.

#22

Softmax: Turning Logits into Probabilities

Master the Softmax equation: exponentiation of logits followed by sum normalization.

#23

Next-Token Prediction & Autoregression

See the complete generation loop: predict, sample, append, repeat.

#24

Greedy Decoding vs Random Sampling

Learn why always choosing the highest probability token leads to repetitive and robotic text.

#25

Temperature: Controlling Randomness and Creativity

Learn how the temperature parameter scales logits before Softmax to sharpen or flatten the distribution.

#26

Top-K Sampling: Truncating the Long Tail

Discover how Top-K filtering prunes unlikely tokens to eliminate bizarre hallucinations.

#27

Top-P (Nucleus) Sampling: Adaptive Filtering

Learn why nucleus sampling is superior to fixed Top-K when probability distributions vary in confidence.

#28

The Production Sampling Pipeline

Combine Temperature, Top-K, and Top-P into the unified production generation pipeline.

Level 5 — Training & Optimization

0 / 4 Completed

Cross-entropy loss, backpropagation, gradients, learning rate schedules, and batches.

#29

Pretraining Datasets: Curating Trillions of Tokens

Explore where LLM data comes from: Common Crawl, Wikipedia, GitHub, arXiv, and filtering pipelines.

#30

Cross-Entropy Loss: Measuring Prediction Error

Learn how Cross-Entropy Loss mathematically measures the gap between the predicted probability and the true target token.

#31

Backpropagation: Tracing Gradients in Reverse

See how the chain rule of calculus computes gradients for billions of weights from loss.

#32

Gradient Descent & Optimizers (AdamW)

Learn how AdamW updates model weights using gradients, learning rates, and momentum.

Level 6 — Fine-Tuning & Adaptation

0 / 3 Completed

Instruction tuning, RLHF, LoRA low-rank decomposition, PEFT, and RAG trade-offs.

#41

What Is Fine-Tuning? (From Base Model to Assistant)

Discover the transformation from a raw text completer to a helpful instruction-following AI assistant.

#44

LoRA & PEFT: Parameter-Efficient Fine-Tuning

Learn how Low-Rank Adaptation (LoRA) allows fine-tuning on consumer GPUs by decomposing weight updates.

#48

Fine-Tuning vs RAG: The Architectural Choice

Understand when to retrieve documents (RAG) vs when to modify model behavior and tone (Fine-Tuning).

Level 7 — Applications & AI Systems

0 / 3 Completed

Vector databases, RAG retrieval pipelines, tool calling, autonomous agents, and system design.

#51

RAG: Retrieval-Augmented Generation Architecture

Learn the complete end-to-end RAG pipeline from document ingestion to vector search and augmented synthesis.

#53

Tool Calling & Function Execution

Understand how models output structured function calls (JSON) to interact with external APIs and calculators.

#55

Modern LLM Application Architecture

The blueprint of enterprise AI: UI, Prompt Firewalls, Semantic Caching, RAG, Routing, and Observability.