The Leanpub 60 Day 100% Happiness Guarantee
Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.
See full terms...
Architecture, Training, Inference, and the MiniLLM Project
Understand modern language models from tokens and matrix operations to training, inference, and applied systems. Work through 20 modules with equations, numerical examples, interactive quizzes, notebooks, and a cumulative MiniLLM project.
Interested in this course? Show your support by saying what you'd like to pay for it!
About the Course
Modern LLMs develops a connected understanding of how language models work: how text becomes token IDs, how neural networks turn a context into a probability distribution, how training changes the weights, and how a model becomes part of a useful system.
Across 20 modules, the course covers tokenization and embeddings, Transformer foundations, positional representations, attention, normalization, MoE, state-space and diffusion models, pretraining, efficient inference, quantization, post-training, reasoning, multimodality, retrieval, agents, and evaluation. The final synthesis module assembles the mathematics into a complete description of training and generation.
Equations are developed alongside worked numerical examples and executable code. The practical path includes Jupyter notebooks, exercises with worked solutions, self-check questions, and 415 automatically marked review questions. A cumulative MiniLLM project connects the mechanisms in a trainable teaching implementation, with dense and mixture-of-experts configurations.
The course is intended for readers with some familiarity with machine learning, Python, linear algebra, and probability. A Transformer foundations module provides a route into the architecture before the more specialized mechanisms. Reading routes distinguish the essential first pass from deeper calculations and optional experiments.
About the Instructor
Lead AI/ML Engineer & Researcher | LLMs, AI Agents, RAG | AI Function Lead in FinTech | Author of 3 Bilingual AI/ML Courses | M.Sc. in AI & Computer Science.
Since 2017, I have worked in R&D, built ML and GenAI systems, and advised businesses on AI adoption.
Education and research:
- Physics at Kharkiv University;
- MIPT University master's program in Modern Artificial Intelligence.
Thesis and publications: LLMs, Learning and Reasoning at the Inference Stage.
Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.
See full terms...
We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.
(Yes, some authors have already earned much more than that on Leanpub.)
Learn more about writing on Leanpub
If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).
Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.
Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.
Learn more about Leanpub's ebook formats and where to read them
You can use Leanpub to easily write, publish and sell in-progress and completed ebooks and online courses!
Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks.
Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. (Or, if you are producing your ebook your own way, you can even upload your own PDF and/or EPUB files and then publish with one click!) It really is that easy.