Books

Building an LLM demo is easy. Running one reliably at scale is not. Production LLMOps shows you how to design, deploy and operate real-world LLM systems, covering RAG, agents, fine-tuning, evaluation, CI/CD, observability, security and more, with practical code you can adapt for production.

A from-scratch AI/ML course that treats you like an engineer, not a tourist — three modules covering language-as-numbers, the math foundations, and neural networks, each concept built in raw Python first, then PyTorch, so you always know what's really happening under the hood.

The eight volumes before this one each teach a single domain, and each is deliberatelyself-contained. The exams do not ask about domains — they ask about systems, and a system spansall of them at once. "A retrieval system is slow, expensive and occasionally wrong — which do you fix first?" needsretrieval, optimisation and operations together. Every one of the 150 questions here crosses atleast two domains, because that is the specific thing a single-domain book cannot teach you.

"The model is safe." "The filter is effective." "We red-teamed it and found nothing." "Wereviewed a sample and it looked fine." Each of those is a claim about evidence, and each is unfalsifiable as stated. Reviewing thirtyoutputs and finding no problems is consistent with a failure rate of one in eleven. Threehundred tests against a thousand possible failure modes leave seven hundred nobody looked at. This book supplies the missing arithmetic — and it was written without generating a singleharmful output to study.

Quantise the weights. Batch the requests. Add a draft model. Prune what you can. Shorten thecache. A long list of techniques and a short list of reasons. This book measures the reason first: the machine streams memory at 22.54 GB/s and computes at116.58 GFLOP/s, so anything performing fewer than 5.17 operations per byte is waiting. Decodingperforms 0.22. Every technique in the book is then measured against that one number — andseveral turn out to be addressing the wrong side of it.

هذا الكتاب هو دليل مختصر وموضّح بالرسوم لأي شخص يرغب في فهم الآلية الداخلية للنماذج اللغوية الضخمة، سواء في سياق المقابلات أو المشاريع أو بدافع الفضول الشخصي.

The practitioner's guide to policy-space response oracles: one 84-line loop, one readable repository, and every claim backed by a committed experiment — including the ones that came out wrong.

Use LoRA because it forgets less. Keep the learning rate low. Mix in some general data. Stopearly. Four pieces of advice everyone repeats and almost nobody quantifies. This book measures each one — and two turn out to be doing something other than what they arecredited with. LoRA's retention is governed by a scaling constant, not by its parameterefficiency. Early stopping bounds the damage without separating it from the gain. Everyexperiment reports two numbers: the new task, and the capability you were not trying tochange.

Vector databases give you a similarity metric, an index with four tuning parameters, acompression option and a way to filter — and almost no guidance on what any of it costs. This book builds each one from scratch and measures it. The proximity graph, the invertedfile, the product quantiser: implemented in NumPy, included with the text, and checkedagainst exhaustive search — so every recall figure here is exact rather than estimated.

A machine can hand you a grouping that is confident, stable, internally consistent, and seven times worse than the one it found a moment earlier. Nothing in the output says so.This book works k-means through completely on twelve bakery customers, small enough that every number is printed and checkable. You will build the method from nothing, see exactly where it succeeds, and see exactly where it fails silently.Fifty-eight figures, every one captured from a running implementation.

Every deep learning tutorial shows you the code. Almost none show you the idea. This is the book to read first - before the frameworks, before the maths notation, before the course you've already paid for. One example, followed all the way through, from a random guess to a network that works. By the end you'll understand what backpropagation actually does, why gradients matter, and what's really happening while your model trains. No calculus required.

Prompting has more advice than evidence. This book measures it instead: a model reading apattern it has never seen, the same model failing at a task in one pass and solving itperfectly in four, a decoder that guarantees a format instead of improving the odds, and amodel that is 2.4% accurate while 78.6% confident. Six central claims are built from scratch and measured on a single CPU core. Everythingtaken from published research sits in a grey box marked "Not measured here" — so you neverhave to guess which is which.

Five certifications ask about the same twenty topics, and each one stops at a differentdepth. This book teaches the topic once, properly, then shows you exactly where each examstops — with 61 original practice questions where every wrong option is explained. Every number in it was measured. Every line of code was run. The code is included.

Class imbalance isn’t a problem. Poor methodology is. This book challenges outdated practices and provides rigorous, data-driven alternatives. We focus on selecting the right tools, threshold tuning, real costs (not class frequencies), and strategic evaluation metrics, to build models that work.

From your first JAX script to large-scale AI systems, this book shows how to write faster, cleaner Python for modern computing. Learn the ideas behind JAX through practical examples, real projects and clear explanations that help you build everything from scientific simulations to distributed machine learning.