This book provides a comprehensive introduction to the foundations of Large Language Models (LLMs). It outlines the core concepts and techniques driving modern NLP, starting with pre-training paradigms and architectures like BERT. It explores generative models, scaling laws, and long-sequence modeling. Key sections detail prompting strategies such as chain-of-thought, alongside alignment methods including instruction fine-tuning and Reinforcement Learning from Human Feedback (RLHF). The text also covers efficient inference techniques, decoding algorithms, and optimization strategies, serving as an educational resource for understanding the mechanisms behind intelligent language systems.