Hugging Face Transformers: Introduction to Pretrained Models

Course details

Looking to expand your skill set in deep learning? Find out how to use Hugging Face transformers to build natural language processing (NLP) applications. In this course, instructor Kumaran Ponnambalam shows you how to build models quickly and easily using pretrained transformers from the Hugging Face library.

Explore models designed for common NLP use cases such as question-answering, text summarization, text generation, translation, and more. Kumaran gives you tips for customizing models with transfer learning to meet the needs of specific use cases—improving your performance and lowering your costs along the way. Develop your know-how to identify and overcome common modeling challenges to ensure successful, error-free deployments. Take this course to ensure that you’re adhering to best practices and industry standards when you start applying your new skills on the job.

Learning objectives
Explore models designed for common NLP use cases such as question-answering, text summarization, text generation, translation, and more.
Learn tips for customizing models with transfer learning to meet the needs of specific use cases—improving your performance and lowering your costs along the way.
Identify and overcome common modeling challenges to ensure successful, error-free deployments.

Concepts

Introduction

Building NLP apps with Transformers
Setting up the exercise files

Question-Answering (Qu-An)

Question-answering in NLP
Types of question-answering
Building a Qu-An pipeline
Evaluating Qu-An performance

Text Summarization

Text summarization in NLP
The BART model architecture
Summarization with pipelines
The ROUGE score
Evaluating with ROUGE

Natural Language Generation

Natural language generation (NLG) in NLP
Content creation with Transformers
Conversation generation
Chatbot conversation example
Machine translation in NLP
Translating with Hugging Face Transformers

Customizing Models with Transfer Learning

Training a custom model
Loading a Hugging Face dataset
Encoding and preprocessing the dataset
Customizing the model architecture
Training the sentiment model
Predicting with the custom model

Deploying and Using Hugging Face Models

Inference challenges with Transformers
Customizing pretrained models
Model compression overview
Serving multiple models

Conclusion

Continuing with Hugging Face