This course introduces undergraduate students to the fundamentals of large language models (LLMs), covering their architecture, training, and real-world applications. Students will explore transformer-based models, learning how they process and generate human-like text. Topics include pre-training and fine-tuning techniques, prompt engineering, ethical challenges, and deployment strategies. Through hands-on projects using frameworks like Hugging Face and DeepSeek APIs, students will build practical skills in developing LLM-powered applications such as chatbots, summarization tools, and code assistants. By the end of the course, students will understand both the technical foundations and societal impacts of LLMs, preparing them for careers in AI and data science.

Note: To pass the course, apart from obtaining a minimum of 40% in the overall mark, a student must also obtain a minimum mark of 30% in both continuous assessment and examination components.