Core Programming AI

Introduction to Large Language Models

1 Lesson

About this course

Introduction to Large Language Models is an advanced artificial intelligence course that explores the architecture, training, and applications of modern language models that have revolutionized natural language processing. The course covers foundational concepts including transformer architectures, attention mechanisms, tokenization strategies, and scaling laws, alongside practical techniques like prompt engineering and parameter-efficient fine-tuning (such as LoRA). Through hands-on experiments using frameworks like Hugging Face Transformers and OpenAI APIs, students will build and evaluate practical applications such as chatbots, code generation tools, and text summarization systems. By the end of the course, students will be equipped to leverage foundation models for complex reasoning and generation tasks while understanding the technical challenges and responsible deployment of large-scale AI systems.

Learning objectives

Understand the core concepts behind modern Large Language Models, including transformer architectures, attention mechanisms, and scaling laws.

Apply advanced prompt engineering and in-context learning techniques to guide language models in complex reasoning and text generation tasks.

Implement pre-training and parameter-efficient fine-tuning methodologies (e.g., LoRA) using industry-standard frameworks like Hugging Face.

Develop, evaluate, and optimize practical LLM applications, such as chatbots, summarization systems, and code synthesis tools.

Design an innovative, LLM-driven application that addresses a real-world need, critically assessing the ethical implications and responsible deployment of powerful foundation models.

Introduction to Large Language Models

About this course

Course Outline