Zero to LLM

Most people interact with LLMs through APIs. Few have trained one.

This workshop changes that. We will build a small language model from scratch using Andrej Karpathy's nanoGPT library, covering the core mechanics that power every frontier model in production today.

You will leave with working code, a real mental model for how transformers learn, and sharper intuition for the tools you use every day.

All experience levels welcome. Bring a laptop. GPUs helpful, not required.

nanoGPT is an open-source library by Andrej Karpathy, former head of AI at Tesla and founding member of OpenAI, built to make training GPT-style models as simple and readable as possible.

Note:

- Unfortunately, no food is offered. Please bring your own lunch.
- Students should never miss class to attend optional programming. The Deans’ Office will not support requests for absences due to participation in any non-class activity or Booth-sponsored event as excused. 

Artificial Intelligence [AI] Club (E/W) | Website | View More Events

Contact the organizers