Building a Transformer from Scratch Workshop
The Building a Transformer from Scratch workshop, part of the Workshops @ Kempner series, focuses on understanding and building a language model. We will dive into the model components, training pipeline, and ingredients of a typical end-to-end language model set-up.
Date: Tuesday November 12th
Time: 1 – 4 pm
Location: Kempner Large Conference Room (SEC 6.242)
Presenters: Nikhil Anand and Ella Batty
Who can attend this workshop? Open to the Kempner community. Harvard affiliates may join given availability.
What will attendees learn from this workshop?
- The components of a standard decoder-only transformer
- How to code and train a language model from scratch
Prerequisite:
- Familiarity with PyTorch framework and Python programming
- Familiarity with foundational machine learning topics such as feedforward networks and gradient descent
Registration:
Please register your interest as soon as possible here. Space is limited.
Contact Information:
For any questions about the workshop, please contact kempnereducation@harvard.edu