All Sheets
Practical cheat sheets to help you learn and build faster.
Tokens vs Words vs Characters — Visual LLM Guide
An 8-page visual guide explaining tokens, words, and characters in AI, with tokenization examples, conversion formulas, context windows, API cost calculations, and practical Python code.
Vector Search vs Traditional Search — Visual Guide to BM25, Embeddings & Hybrid Search
A 13-page visual guide comparing keyword (BM25), vector, and hybrid search, with embedding models, ANN indexes, FAISS and Elasticsearch examples, ranking techniques, and evaluation checklists.
Tensors in AI
A 15-page visual guide to tensors in AI and deep learning. Master tensor rank, shape, indexing, reshaping, broadcasting, matrix multiplication, attention shapes, memory, autograd, and practical PyTorch operations.
Parameters vs Hyperparameters vs Model Weights
An 11-page visual beginner’s guide to parameters, hyperparameters, and model weights in machine learning, with diagrams, worked examples, tuning strategies, model-size calculations, and practical Python examples.
Attention in AI
A 14-page visual guide to Attention in AI, covering Q/K/V, scaled dot-product attention, self & cross-attention, masking, multi-head attention, positional encoding, KV cache, FlashAttention, and practical NumPy + PyTorch code.
CNN vs RNN vs Transformer
An 18-page visual beginner’s guide to CNNs, RNNs/LSTMs, and Transformers, covering how each architecture works, when to use it, attention, convolution, sequence memory, training, model selection, and practical PyTorch code.
How Does Generative AI Actually Work?
A 14-page visual guide to how generative AI actually works—from tokens, embeddings and transformers to training, reasoning models, sampling, diffusion, RAG and AI agents. Includes diagrams, comparison tables, Python snippets and practical decision guides.
LLM or Traditional ML?
A practical visual decision guide for choosing between LLMs, traditional machine learning, pretrained models, rules, and hybrid approaches—with flowcharts, cost comparisons, deployment trade-offs, and Python examples.