Course: Large Language Models: Build, Fine-Tune and Deploy LLMs

Build a complete Retrieval-Augmented Generation pipeline that connects semantic retrieval with LLM generation. Explore contrastive triplet datasets, bi-encoder fine-tuning, embedding normalization, vector stores, efficient top-k search, and knowledge-grounded inference.

Build a practical LLM-powered flashcard application from the ground up. Generate structured vocabulary cards with translations, definitions, examples, and mnemonics, enrich them with images and audio, store them locally, and …

Explore the foundations of statistical and neural language modeling. Learn how n-gram models predict the next token, how Laplace smoothing handles unseen sequences, how perplexity evaluates model quality, and how …

Take a hands-on look inside a modern transformer by implementing key components of a LLaMA-style architecture. Explore RoPE, RMSNorm, self-attention, transformer layers, optimization, classification, and how pretrained models can be …

Explore how foundation models can be adapted for specialized tasks. Learn prompt engineering, dataset preparation, model-loading and memory optimization, experiment tracking, grid search, and parameter-efficient fine-tuning with LoRA, IA³, and …

Set up your JetBrains IDE and supporting development environment for the course. Get familiar with the tools, libraries, and workflow you’ll use to implement, run, test, and evaluate LLM and …

Explore the foundations of natural language processing through a practical sentiment-classification problem. Learn about data exploration, preprocessing, tokenization, embeddings, and classical machine learning approaches including kNN, Bag of Words, Naive …

Watch an introduction to Mastering Large Language Models and explore the course journey from NLP foundations and statistical language modeling to transformers, fine-tuning, Retrieval-Augmented Generation, and practical LLM-powered applications.