A practical introduction to Large Language Models (LLMs)

A Certificate of Participation is awarded to participants who contribute constructively to weekly discussions and exercises/learning activities for the duration of the course.

This tutor-led, cohort-based online course is 7-weeks in duration and is made up of 5 teaching units.

Unit 1 - Introduction to Large Language Models (LLMs)

This unit will introduce the underlying concepts of Generative AI, focusing on Large Language Models (LLMs). Participants will learn what LLMs are, their history, development, and the basic principles of their operation. This unit sets the stage for a deeper exploration of the capabilities, benefits, and limitations of these technologies. 

Learning objectives: 

• To understand what Large Language Models are and their role in the Generative AI landscape. 

• To identify the key components and principles that enable LLMs to generate text. 

• To discuss the historical development and evolution of LLMs. 

• Discuss the potential impact of LLMs on various sectors.

Unit 2 - Building blocks of LLMs

This unit delves deeper into the technical aspects of LLMs, including large datasets, transformer architecture, self-attention mechanisms, and large parameter counts. Students will learn about pre-training, fine-tuning, reinforcement learning, and the generative capabilities of LLMs, setting a foundation for understanding practical applications. 

Learning objectives: 

• To gain a good understanding of the architecture and mechanisms that power LLMs. 

• To learn about the importance of large data sets in training LLMs and how biases in these datasets can influence model outputs. 

• To understand the concepts of pre-training, fine-tuning, and their importance in developing specialized LLM applications. 

• To explore the generative capabilities of LLMs, including text generation and prediction.

Unit 3 - Introduction to Prompt Engineering

This unit addresses an introduction to popular LLMs such as ChatGPT, Claude, Gemini, and Copilot. It focuses on practical prompt engineering, and focusing on writing prompts that result in effective model responses. Students will complete hands-on activities to create, refine, and evaluate prompts, understanding their impact on model output quality and bias. 

Learning objectives: 

• To write effective prompts for diverse applications and contexts. 

• To evaluate and refine prompts to improve interaction quality with LLMs. 

• To understand the impact of prompt design on output bias and methods to mitigate it. 

• To gain practical experience through prompt-based exercises and examples.

Unit 4 - Prompt Tuning and Advanced Interaction Strategies

This unit focuses on prompt tuning and advanced strategies to further customize LLM outputs. Participants will cover techniques for prompt tuning, including zero-shot, few-shot learning, and chain-of-thought prompting. These will be applied to a mini-project. We will discuss strategies to overcome limitations and biases through advanced prompt engineering. 

Learning objectives: 

• To master prompt tuning techniques for task-specific enhancements. 

• To implement advanced promptng strategies to navigate limitatons. 

• To develop a refined understanding of how prompt structure influences LLM responses. 

• To engage in exercises that apply advanced prompt engineering in various contexts.

Unit 5 - Practical Applications and Future Trends

This unit is dedicated to exploring real-world applications of LLM tools and technologies and the future of LLMs. Participants will review case study examples and engage in small project work that applies their LLM of choice (ChatGPT, Claude, Gemini, Copilot, …) to solve practical problems. This unit will encourage students to think critcally about the future impact and evolution of LLMs in society. 

Learning objectives: 

• To apply LLM use to real-world scenarios. 

• To critcally assess potential future developments and impacts of LLM technology. 

• To complete a small project demonstrating practical LLM applications. 

• To participate in discussions on responsible use and long-term considerations of LLMs.