Large Language Models and Generative AI

Catalog description

This course provides a comprehensive study of Large Language Models (LLMs), exploring their theoretical foundations, architectures, and applications. Topics include transformer architecture, data wrangling, tokenization, pre-training, fine-tuning, and model optimization techniques like distillation and quantization. Students will learn evaluation metrics, multimodal LLM designs, and real-world applications in Natural Language Processing (NLP) and beyond. Ethical considerations, bias, safety, and security challenges are also addressed. Through lectures, hands-on projects, and presentations, learners will gain skills to design, evaluate, and deploy LLMs effectively.