Large Language Models

Course Description

This advanced course imparts a comprehensive understanding of Large Language Models (LLMs) with a focus on their architecture, application paradigms, and ethical implications. Structured over 15 weeks, the course is tailored for students with a background in machine learning and natural language processing. It features hands-on training, in-depth analysis of scholarly papers, a midterm examination, and a final project centering on the development of a practical LLM application.

Learning Goals

Upon completing this course, students will be able to:

1. Understand the architectural intricacies of leading LLMs like BERT, T5, and GPT-3.

2. Utilize specialized techniques such as few-shot learning, prompt engineering, and in-context learning in LLMs.

3. Investigate and address ethical concerns including bias and data privacy.

4. Implement a real-world LLM application as part of the final project.

5. Critically evaluate peer projects through a formal review process.

Grading

• Participation: 10%

• Midterm Exam: 25%

• Peer Reviews of Final Project: 5%

• Final Project: 60%

Final Project

The final project mandates students to create a real-world application using a large language model. The project involves data pre-processing, model training/fine-tuning, evaluation, and documentation. Students will also participate in peer reviews to critically evaluate the projects of their peers. The deliverables include a functional LLM application and a research paper.

Course Outline

• Introduction
  • Large Language Models?
• LLM Stacks
  • Generative AI Infrastructure Stack
  • LLM Application Architectures
  • LLM App Ecosystem
• AI Agents
  • AutoGen
  • AutoGen AutoScraper Agent
• LLM Fine-tuning
  • Fine-Tuning LLMs with Hugging Face AutoTrain
• Retrieval Augmented Generation (RAG)
• Parameter-Efficient Fine-Tuning (PEFT)
  • PEFT for LLMs
  • PEFT in HuggingFace Libraries
• Q-Learning
  • Q-Star (Q*)