To receive a Zoom link after registering above, please fill out the affiliations form if you have not done so at least once before: https://dlab.berkeley.edu/affiliations
Trying to register, but not affiliated with the UCB campus? If you are from Berkeley Lab (LBL), CZ Biohub, or other organizations, please register via our partner portals here.
Location: Remote via Zoom. Link will be sent on the morning of the event.
Recordings: This D-Lab workshop will be recorded and made available to UC Berkeley participants for a limited time. Your registration for the event indicates your consent to having any images, comments and chat messages included as part of the video recording materials that are made available.
Date & Time: This workshop runs from 3pm-5pm on:
• Wednesday, April 17
Start Time: D-Lab workshops start 10 minutes after the scheduled start time (“Berkeley Time”). We will admit all participants from the waiting room at that time.
Description
This workshop offers a general introduction to the GPT (Generative Pretrained Transformers) model. We will explore how they reflect and shape our cultural narratives and social interactions, and which drawbacks and constraints they have. We will explore the transformer architecture upon which GPTs are built, how GPTs encode natural language into embeddings, and how it predicts text. We will also use geometric similarity approaches to represent varying types of similarity between words.
Requirements
Prerequisites: We recommend attending D-Lab’s Python Fundamentals and Python Data Wrangling prior to this workshop. We additionally recommend a basic understanding of HTML and CSS.
GitHub Repository: https://github.com/dlab-berkeley/GPT-Fundamentals
Software Requirements:Installation Instructions for Python Anaconda
Is Python Not working on your laptop? Attend the workshop anyway, we can provide you with a cloud-based solution until you figure out the problems with your local installation.
Feedback: After completing the workshop, please provide us feedback using this form
Questions? Email: dlab-frontdesk@berkeley.edu