Skip to content

Latest commit

 

History

History
108 lines (71 loc) · 6.87 KB

README.md

File metadata and controls

108 lines (71 loc) · 6.87 KB
Raw

Open In Colab

AI Summer

Summary repository for AI Summer 2022. Introduction to Transformer models, with practical applications to inferencing and training

Presented by Vanderbilt Data Science Institute data scientists:

  • Dr. Jesse Spencer-Smith, Chief Data Scientist
  • Dr. Charreau Bell, Senior Data Scientist
  • Umang Chaudhry, Data Scientist

Overview

The objective of these workshops is to develop foundational skills in understanding, inferencing and training Transformer models primarily using HuggingFace, an extremely user-friendly API for transformers.

Course Coverage

Getting the Most out of this Course

To get the most out of this crash course in Python:

  • Open Colab (workbook) notebooks and actively write code along with the instructor
  • Actively participate in discussion
  • Actively participate in breakout rooms
  • Perform homework assignments before coming to class the next day
  • Relax your mind and ask questions
  • Let us know how you are doing using Fastcups at https://cups.fast.ai/vanderbilt-ai-summer!

Pre-Workshop Preparation

  • Sign up for a Google Collaboratory account. The free account should be sufficient, but you will get more compute (and longer running times) if you sign up for Colab Pro at ~$5/month.
  • Sign up for a Hugginface.co account. Again, the free account should be sufficient.
  • Suggested: Preview the book 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.
  • 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!

Workshop Schedule

Mon, May 16 Introduction to Transformers, architecture, Huggingface models, datasets, spaces

Wed, May 18 Text applications / inferencing pipeline / sharing your work interactively with Gradio

Fri, May 20 Training for text / pushing to hub / custom Gradio - see https://github.com/vanderbilt-data-science/ai-summer-gradio

Mon, May 23 Audio models

Wed, May 25 Audio models / Image models

Fri, May 27 Image models

Mon, May 30 Custom models from scratch/special tokens/domain adaptation

Wed, Jun 1 Custom models from scratch/Perceiver IO

Fri, Jun 3 Research Presentation / Whirlwind tour of what's new / Next Steps

Breakout Rooms

During these workshops, we'll have a number of breakout rooms where you'll work with others for discussion or develop code to solve an assignment. Please screenshot or paste your results in the following Google doc:

https://docs.google.com/document/d/15deDo3TBlgue_7ueoHake-O3HoEqCZKBZOHWfmfUlFQ/edit?usp=sharing

Using Fastcups

During a live session, open https://cups.fast.ai/vanderbilt-ai-summer and click on the green, yellow, or red cup to indicate how you are doing! image

Workshop Video Recordings

Video recordings of these workshops can be found at the links below:

AI with Transformers

Note: Titles of the records may say "Office Hours," but they are of the course.

Week 1: Python for AI

VU Python for AI:

Week 2: Transformers

Week 3: Transformers, Vision Transformers, Audio Transformers

Python for AI Resources

Asynchronous (Homework) Assignments

A number of examples will be left to the reader. Please complete these assignments prior to coming to the next day of the course. These homework assignments are designed to augment your understanding of Python, enable you to avoid common pitfalls of programming, resolve known areas of ambiguity that often arise in our new learners, and navigate and understand common errors that Python will throw.

Other Resources

Compute Grants for Vanderbilt Faculty and Students

DGX A100 Compute Grant: https://forms.gle/2mGfEy9DB4JU2GpZ8

Python

Transformers

  • 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.