Transformers & LLMs Tutorials

Attention, the transformer, BERT, GPT, prompting and fine-tuning. Every lesson is free, visual and written in simple English.

In-depth visual guides

Transformers & LLMsSelf-Attention (Q, K, V)

See self-attention in action. Click any word to see where it looks, then step through Q·Kᵀ, scaling, softmax and the weighted sum with real numbers. Multi-head attention, masking, positional encoding, NumPy and PyTorch code.

11 min read2 interactive visualsIntermediate

Transformer & Attention Mechanisms

Motivation & Self-AttentionBeginner · 12 min Scaled Dot-Product & Multi-Head AttentionIntermediate · 12 min Advanced AttentionIntermediate · 14 min

Transformer Architecture & Variants

Architecture & Positional EncodingIntermediate · 12 min Inside the Encoder and Decoder BlocksIntermediate · 12 min Transformer VariantsIntermediate · 12 min BERT Explained: How It Works and Its VariantsBeginner · 15 min

Pretrained Models & LLMs

Generative Modeling & Hugging FaceBeginner · 12 min How an LLM Is TrainedBeginner · 6 min Decoding Strategies & the LLM LandscapeIntermediate · 14 min Adaptation, Quantization & EvaluationIntermediate · 14 min

Prompt Engineering

Prompt FundamentalsBeginner · 10 min Reasoning TechniquesIntermediate · 10 min Structured Output & ReliabilityIntermediate · 12 min Dynamic Prompting with LangChainIntermediate · 12 min Conversational Chains & TracingIntermediate · 12 min

Fine-Tuning Techniques

LoRA and Fine-TuningIntermediate · 7 min The Fine-Tuning DecisionIntermediate · 10 min PEFT Hands-OnAdvanced · 14 min