This course offers a comprehensive deep dive into Large Language Models (LLMs) and Generative AI, covering theoretical foundations, technical architectures, and real-world applications. Students will explore internal mechanisms like pre-training, transfer learning, and task-specific fine-tuning. The curriculum extends to generative models (specifically text-to-image) and their training methods, equipping students with the practical skills needed to master these cutting-edge technologies.

Outline of Lectures

1. LLM Fundamentals
2. The LLM Architecture
3. Pre-training Models
4. Supervised Fine-Tuning
5. Parameter-Efficient Fine-Tuning Techniques and Design Spaces
   • LoRA, QLoRA, Axolotl, DeepSpeed, Adaptation
6. Preference Alignment
   • RLHF: Aligning LLM responses with human expectations using preference datasets and PPO
7. LLMs APP Development
   • LangChain
   • Prompt Engineering
8. Retrieval Augmented Generation (RAG)
9. Agent Framework
10. Multimodal Models 11 Text to Image Generation