Enjoy fast, free delivery, exclusive deals, and award-winning movies & TV shows with Prime
Try Prime
and start saving today with fast, free delivery
Download the free Kindle app and start reading Kindle books instantly on your smartphone, tablet, or computer - no Kindle device required.
Read instantly on your browser with Kindle for Web.
Using your mobile phone camera - scan the code below and download the Kindle app.
Frequently bought together
$44.99
Get it as soon as Saturday, Jul 27
In Stock
Total price:
To see our price, add these items to your cart.
Choose items to buy together.
Customers who bought this item also bought
Page 1 of 1 Start overPage 1 of 1
About the author
Follow authors to get new release updates, plus improved recommendations.
Reviews with images
Useful guide to understand business and technical case for deploying foundation models on AWS
I would recommend this book to anyone (technical and non-technical) who is interested in learning about training foundational models. Given the explosion of GenAI and more specifically foundational models in 2023, I purchased this book to learn more about when, why, and how to pre-train these models for specific use-cases. As someone who is new to machine learning, let alone pre-training foundational models, I have found this book very digestable. It does a great job bridging high level considerations with deep and thoughtful technical guidance, and provides opinionated guidance on each step of the decesion making process.
Top reviews from the United States
There was a problem filtering reviews right now. Please try again later.
Reviewed in the United States on July 19, 2023
Useful guide to understand business and technical case for deploying foundation models on AWS
Reviewed in the United States on July 19, 2023
I would recommend this book to anyone (technical and non-technical) who is interested in learning about training foundational models. Given the explosion of GenAI and more specifically foundational models in 2023, I purchased this book to learn more about when, why, and how to pre-train these models for specific use-cases. As someone who is new to machine learning, let alone pre-training foundational models, I have found this book very digestable. It does a great job bridging high level considerations with deep and thoughtful technical guidance, and provides opinionated guidance on each step of the decesion making process.
Reviewed in the United States on July 19, 2023
Images in this review
Reviewed in the United States on June 5, 2023
In the fast-paced world of ML, where LLMs are at the forefront of innovation, keeping up with the rapid advancements can be challenging. However, Emily's book, announced just before the LLM boom, provides a solid foundation that enables you to navigate these developments with ease. It has proven to be a timely resource for those keen on understanding and leveraging the power of LLMs.
Book Summary:
Comprehensive Coverage: The book offers an in-depth exploration of training vision and large language models, covering all stages from project ideation, dataset preparation, training, evaluation, to deployment for large language, vision, and multimodal models.
Expert Guidance: Authored by Emily Webber, a seasoned AWS and machine learning expert, the book provides industry-expert guidance and practical advice, making it a valuable resource for both beginners and experienced practitioners.
Practical Approach: The book is replete with practical examples and code samples that help readers understand how to pretrain and fine-tune their own foundation models on AWS and Amazon SageMaker.
Bias Detection: A unique feature of the book is its focus on bias detection and pipeline monitoring, which are critical aspects of model development and deployment.
Advanced Topics: The book delves into advanced topics like large-scale distributed training, hyperparameter selection, and model distribution, providing readers with a deep understanding of these complex areas.
Future Trends: The final chapter on future trends in pretraining foundation models gives readers a glimpse into what's next in the field, keeping them ahead of the curve.
In conclusion, if you're looking to ride the wave of LLMs and want to do so using AWS, this book is a must-read. It's more than just a guide; not a beginner's book!!! It's a comprehensive resource that empowers you to navigate the fast-paced world of ML with confidence and proficiency. Emily Webber's expertise shines through each page, making this book an invaluable asset for anyone in the field. As LLMs continue to evolve and revolutionize various sectors, this book stands as a testament to their transformative potential and a guide for those looking to be part of this exciting journey. This is just the start..... Transformers......... !!!
Riding the Wave of Large Language Models with Emily Webber.
Reviewed in the United States on June 5, 2023
As a long-time admirer of Emily Webber and an enthusiast of SageMaker and Large Language Models (LLMs), I've been eagerly anticipating the release of this book. As a regular user of AWS, I can confidently state that this book is a substantial contribution to the advanced field of Machine Learning (ML).Reviewed in the United States on June 5, 2023
In the fast-paced world of ML, where LLMs are at the forefront of innovation, keeping up with the rapid advancements can be challenging. However, Emily's book, announced just before the LLM boom, provides a solid foundation that enables you to navigate these developments with ease. It has proven to be a timely resource for those keen on understanding and leveraging the power of LLMs.
Book Summary:
Comprehensive Coverage: The book offers an in-depth exploration of training vision and large language models, covering all stages from project ideation, dataset preparation, training, evaluation, to deployment for large language, vision, and multimodal models.
Expert Guidance: Authored by Emily Webber, a seasoned AWS and machine learning expert, the book provides industry-expert guidance and practical advice, making it a valuable resource for both beginners and experienced practitioners.
Practical Approach: The book is replete with practical examples and code samples that help readers understand how to pretrain and fine-tune their own foundation models on AWS and Amazon SageMaker.
Bias Detection: A unique feature of the book is its focus on bias detection and pipeline monitoring, which are critical aspects of model development and deployment.
Advanced Topics: The book delves into advanced topics like large-scale distributed training, hyperparameter selection, and model distribution, providing readers with a deep understanding of these complex areas.
Future Trends: The final chapter on future trends in pretraining foundation models gives readers a glimpse into what's next in the field, keeping them ahead of the curve.
In conclusion, if you're looking to ride the wave of LLMs and want to do so using AWS, this book is a must-read. It's more than just a guide; not a beginner's book!!! It's a comprehensive resource that empowers you to navigate the fast-paced world of ML with confidence and proficiency. Emily Webber's expertise shines through each page, making this book an invaluable asset for anyone in the field. As LLMs continue to evolve and revolutionize various sectors, this book stands as a testament to their transformative potential and a guide for those looking to be part of this exciting journey. This is just the start..... Transformers......... !!!
Images in this review
Reviewed in the United States on March 23, 2024
Customizing data sets to be unique in purpose, depth, and completeness is recommended to stay competitive in this rapidly evolving landscape. My first pass through the content of this book helped me to understand that the incorporation of continuous learning and keeping humans in the loop throughout the application workflow is key to leveraging the full potential of LLMs.
The most important takeaway to me was the relationship and scaling between open-source ML models and fine-tuning them for specific tasks. This book provided an understanding of this relationship, describing it, identifying constants involved, and determining the appropriate scaling needed for optimization.
The author did a great job of breaking down the components of Pretraining for this novice. I can only assume that there are tidbits in this book for all levels of AI enthusiasts delving into the preparation of LLMs for purpose. Thank you for this solid information!
LLM Applications proficiency starts with the quality of input data and fine-tuning for purpose.
Reviewed in the United States on March 23, 2024
As a Sr. Fullstack engineer and punk AI hacker recently immersed in the world of building applications with Large Language Models (LLMs), I get that an emphasis on human-centered design will be vital in our LLM interactions going forward. This book reinforces that view with discussions of dataset preparation, fine-tuning, model evaluation, and human labeling as critical aspects that accelerate the ability of LLM applications.Reviewed in the United States on March 23, 2024
Customizing data sets to be unique in purpose, depth, and completeness is recommended to stay competitive in this rapidly evolving landscape. My first pass through the content of this book helped me to understand that the incorporation of continuous learning and keeping humans in the loop throughout the application workflow is key to leveraging the full potential of LLMs.
The most important takeaway to me was the relationship and scaling between open-source ML models and fine-tuning them for specific tasks. This book provided an understanding of this relationship, describing it, identifying constants involved, and determining the appropriate scaling needed for optimization.
The author did a great job of breaking down the components of Pretraining for this novice. I can only assume that there are tidbits in this book for all levels of AI enthusiasts delving into the preparation of LLMs for purpose. Thank you for this solid information!
Images in this review
Reviewed in the United States on September 27, 2023
