Summary repository for AI Summer 2025. Introduction to generative AI, with practical applications for inferencing and training May 5-30, 2025
Presented by Vanderbilt Data Science Institute data scientists:
- Dr. Jesse Spencer-Smith, Chief Data Scientist
- Dr. Charreau Bell, Senior Data Scientist
- Myranda Shirk, Senior Data Scientist
- Umang Chaudhry, Senior Data Scientist
- Dr. Abigail Petulante, DSI Postdoctoral Fellow
The objective of these workshops is to develop foundational skills in understanding, inferencing and training generative AI models and other transformer models.
Practice your Python skills using the below documents. Choose either a Google Colab for interactive programming environment, or alternatively read through the Google Doc.
You’ll want to use the most advanced AI chat model that you can get access to. To get a headstart, please create an account with OpenAI. We will go over instructions on how to create API keys and more during the sessions.
Think about any data you might want to bring to the workshop. Also begin thinking about any projects you might want to accomplish during our month. We’ll have office hours for you to work with us to get your first project off the ground!
Session will run live from 11am-1pm, with an office hour from 1pm to 2pm (all times Central).
Week 1, 5/5 - 5/9: Introduction to Generative AI Models, AI Augmented Programming, and Secure Data Practices.
Monday: Introduction to Generative AI Models, AI Augmented Programming (cursor, windsurf, replit etc.)
Wednesday: API Keys, Secure Data Practices
For Wednesday's course, please download and sign up for the following:
- Download LMStudio
- Register an account on HuggingFace and generate an API Token
- Create an account, then navigate to Account -> Access Tokens -> Create New Token -> Write
- Give your token a name, and save the Token Key (it will only display this once, so save it!!)
No class Friday, May 9 (Vanderbilt Commencement)
Week 2, 5/12 - 5/16: Reasoning Models, Introduction to Agents, Multimodal Models and Reinforcement Learning
Monday: Introduction to AI Models, Reasoning Models, Tool Use and Introduction to Agents
Breakout Room Working Document
Wednesday: Langflow, Multimodal Models
Friday: Reinforcement Learning
Monday: Parameter Efficient Finetuning, Introduction to RAG
Wednesday: Advanced RAG Techniques, LangChain and LangGraph
No Class Friday, May 23 (Memorial Day Weekend)
No class Monday, May 26 (Memorial Day)
Wednesday: Building Agents, Building Tools
Friday: Advanced Tools, MCP, A2A, Agentic Frameworks
Remember we are all learning and exploring
- Please share your video upon entering the room and unmute
- Share your screens--someone volunteer to share their screen upon entering, and everyone be ready to share your screen to show what you’ve found
- Make notes of what you’ve discussed in the Response Reports below
- Everyone be ready to report out (random)
- Make some friends
- Breakout Rooms Worksheets
Google Docs has a limit of 100 people viewing/editing a document at one time.
Please be sure your display name is set in Zoom. If you are in one of the following special groups, please pre-pend your name with one of the following qualifiers.
- Data Science for Social Good: DSSG
- Center for AI in Protein Dynamics: Protein
- If you are in a lab and would like your own breakout room: Labname (keep it short, please!)
- If you are faculty and would like to be in a breakout room with other faculty: Faculty
For example, I might be DSSG-Jesse Spencer-Smith
Video recordings of these workshops can be found on our YouTube channel
Looking for the code resources for Summer 2024? View the 2024 repo here.
- Prompt Engineering paper https://arxiv.org/abs/2302.11382
- Prompt Engineering Courserea Course: https://www.coursera.org/learn/prompt-engineering
- Visual overview of Generative AI from 3Blue1Brown: https://www.youtube.com/watch?v=wjZofJX0v4M
- Semester-long course on transformer models, DS 5690. Graduate students and advanced undergraduates can register by contacting Jesse Spencer-Smith. We welcome auditing by a select number of postdoctoral fellows, and drop-ins from faculty!
DGX A100 Compute Grant: https://forms.gle/2mGfEy9DB4JU2GpZ8
- Natural Language Processing with Transformers by Lewis Tunstall, Leandro von Werra and Thomas Wolf. If you are affiliated with Vanderbilt University, you can access this pre-print book (and any book by O’Reilly) free by logging into O'Reilly Media using your Vanderbilt email address. Vanderbilt licenses all content from O’Reilly. The book covers Transformers for purposes beyond text.
To get the most out of this workshop:
- Open Colab (workbook) notebooks and actively write code along with the instructor
- Actively participate in discussions
- Actively participate in breakout rooms
- Work on homework assignments before coming to class
- Relax your mind and ask questions