Event

We will learn how to train a fully-working Transformer on our laptops. Uncovering how training a Next-Token-Prediction Transformer that mimics a calculator adding two numbers together works efficiently.

In the following Part. We will look into how the internals work and why our own trained models work.

Bring a laptop with Python and PyTorch preinstalled with you. If you have any questions you can contact me on DECT 9560.

Any updates on location and time will be written here. Also more information in the Repository.

UPDATE ORT: Near Workshopspace 1