Your key to transformer based NLP, vision, speech, and multimodalities
Key Features
● Transformer architecture for different modalities and multimodalities.
● Practical guidelines to build and fine-tune transformer models.
● Comprehensive code samples with detailed documentation.
Description
This book covers transformer architecture for various applications including NLP, computer vision, speech processing, and predictive modeling with tabular data. It is a valuable resource for anyone looking to harness the power of transformer architecture in their machine learning projects.
The book provides a step-by-step guide to building transformer models from scratch and fine-tuning pre-trained open-source models. It explores foundational model architecture, including GPT, VIT, Whisper, TabTransformer, Stable Diffusion, and the core principles for solving various problems with transformers. The book also covers transfer learning, model training, and fine-tuning, and discusses how to utilize recent models from Hugging Face. Additionally, the book explores advanced topics such as model benchmarking, multimodal learning, reinforcement learning, and deploying and serving transformer models.
In conclusion, this book offers a comprehensive and thorough guide to transformer models and their various applications.
What you will learn
● Understand the core architecture of various foundational models, including single and multimodalities.
● Step-by-step approach to developing transformer-based Machine Learning models.
● Utilize various open-source models to solve your business problems.
● Train and fine-tune various open-source models using PyTorch 2.0 and the Hugging Face ecosystem.
● Deploy and serve transformer models.
● Best practices and guidelines for building transformer-based models.
Who this book is for
This book caters to data scientists, Machine Learning engineers, developers, and software architects interested in the world of generative AI.
Table of Contents
1. Transformer Architecture
2. Hugging Face Ecosystem
3. Transformer Model in PyTorch
4. Transfer Learning with PyTorch and Hugging Face
5. Large Language Models: BERT, GPT-3, and BART
6. NLP Tasks with Transformers
7. CV Model Anatomy: ViT, DETR, and DeiT
8. Computer Vision Tasks with Transformers
9. Speech Processing Model Anatomy: Whisper, SpeechT5, and Wav2Vec
10. Speech Tasks with Transformers
11. Transformer Architecture for Tabular Data Processing
12. Transformers for Tabular Data Regression and Classification
13. Multimodal Transformers, Architectures and Applications
14. Explore Reinforcement Learning for Transformer
15. Model Export, Serving, and Deployment
16. Transformer Model Interpretability, and Experimental Visualization
17. PyTorch Models: Best Practices and Debugging
fabio santana –
I work as a technical project manager and purchased this book to not only learn the fundamentals of transformer models but also understand how to develop and implement projects in practice using these models. This book fulfills both goals: teaching the fundamentals and providing step-by-step, practical examples.The first chapter does a great job in detailing the architecture of transformer models. Since I do not have expertise in this domain, some terminology went over my head but the book provides enough information for you to perform additional research and dive deeper into any related topics as needed. The information is structured in a logical sequence and broken down into small pieces, making it easy to follow how data is processed through each layer of the transformer architecture. The book also provides a link to a google drive folder with colored versions of all illustrations, which was helpful when trying to visualize the different steps (embedding, positional encoding, attention mechanism, etc.).The next chapters contain several hands-on practical examples of how to implement these models, starting with the basics of creating custom tokenizers (which led me to watch videos on the history and inner workings of Byte Pair Encoders (BPEs)) to full blown computer vision, speech processing, and multimodal projects. Since every code example is readily available as jpnyb files (that will take you straight to Google Colab), it is extremely easy for anyone to follow along and create these projects themselves.If you are interested in learning more about transformer models but is a bit overwhelmed with all the content available, this is the perfect book to guide you through in a logical sequence and allow you to learn “by doing” with easy to follow code examples.
sunita –
This book covers the comprehensive topics of ML (NLP, Computer Vision, Audio, Structured Data, RL ..) and how transformer can be applied on those topics. I find this very helpful to understand transformer and it’s application. Specially, I like the approach where the author describes the architecture and goes into application via practical example.
DhavalP –
It’s pretty good book, compare to others. Main thing is that language, content and coding samples which can easily get your experience more informative and learning.