The PYTHON511-PYTHON514 Generative AI and Large Language Models (LLMs) training series introduces practical ways to work with Generative AI and large language models in research and applied settings. Rather than focusing on theory alone, the sessions are designed to help you understand how these tools work, what they can and cannot do, and where they can be applied effectively.
This PYTHON512 course provides hands-on experience in developing and applying large language model (LLM)–based systems for natural language processing (NLP) tasks. Rather than building large models from scratch, the focus is on understanding core machine learning principles, training simple NLP models, and working effectively with pre-trained language models in real-world workflows.
Throughout this course, you will begin by revisiting essential machine learning concepts for text-based tasks and building simple supervised NLP models using raw text datasets. You will then explore how modern pre-trained language models are used in practice, including how to apply them to downstream tasks such as text classification and improve performance through fine-tuning. Using SMS spam detection as a running example, you will compare different model approaches, examine the impact of training parameters, and gain practical experience in managing trained and fine-tuned models. Along the way, we will also discuss key challenges in model development, including computational requirements and data-related biases, to help you make informed modelling choices.
By the end of this course, you will be able to build, train, fine-tune, and manage NLP models using pre-trained architectures, and be well prepared for more advanced large language model applications in subsequent courses.