In this workshop, you'll walk through a complete end-to-end example of using Hugging Face Transformers, involving both our open-source libraries and some of our commercial products.

 

Starting from a dataset containing real-life product reviews from Amazon.com, you'll train and deploy a text classification model predicting the star rating for similar reviews.

 

Along the way, you'll learn how to:

- Explore models and datasets on the Hugging Face Hub,

- Load, prepare and save datasets with the Hugging Face datasets library,

- Load, train and save models with the Hugging Face transformers library,

- Build ML applications with Hugging Spaces to showcase your models,

- Use hardware acceleration with the Hugging Face Optimum library to optimize training and prediction times,

- and maybe a few more things, if we have time!

 

Of course, all code will be shared with you, and you'll be able to use it easily in your own projects.

 

Prerequisites:

• This is a hands-on, code-level workshop all the way. Coding proficiency is required

• Participants don't need to be ML experts, but they must be familiar with basic ML concepts and workflows, as well as Python and Python-based tools for ML (Jupyter, numpy, pandas, etc.).

• Participants must bring their own laptop.

• Prior to the workshop, participants must set up a cloud-based Jupyter environment with GPU support (Google Colab, Amazon SageMaker Studio Lab or Amazon SageMaker Studio) and Git LFS support (https://git-lfs.github.com).

  • No time will be allocated for setupup during the workshop. 

  • Google Colab Paid Version $10 (https://colab.research.google.com/signup)