El. knyga: LLMs in Production: Engineering AI Applications

Learn how to put Large Language Model-based applications into production safely and efficiently.

Large Language Models (LLMs) are the foundation of AI tools like ChatGPT, LLAMA and Bard. This practical book offers clear, example-rich explanations of how LLMs work, how you can interact with them, and how to integrate LLMs into your own applications. In LLMs in Production you will:

• Grasp the fundamentals of LLMs and the technology behind them
• Evaluate when to use a premade LLM and when to build your own
• Efficiently scale up an ML platform to handle the needs of LLMs
• Train LLM foundation models and finetune an existing LLM
• Deploy LLMs to the cloud and edge devices using complex architectures like RLHF
• Build applications leveraging the strengths of LLMs while mitigating their weaknesses

LLMs in Production delivers vital insights into delivering MLOps for LLMs. You’ll learn how to operationalize these powerful AI models for chatbots, coding assistants, and more. Find out what makes LLMs so different from traditional software and ML, discover best practices for working with them out of the lab, and dodge common pitfalls with experienced advice.

Purchase of the print book includes a free eBook in PDF and ePub formats from Manning Publications.

About the book

LLMs in Production is the comprehensive guide to LLMs you’ll need to effectively guide you to production usage. It takes you through the entire lifecycle of an LLM, from initial concept, to creation and fine tuning, all the way to deployment. You’ll discover how to effectively prepare an LLM dataset, cost-efficient training techniques like LORA and RLHF, and how to evaluate your models against industry benchmarks.

Learn to properly establish deployment infrastructure and address common challenges like retraining and load testing. Finally, you’ll go hands-on with three exciting example projects: a cloud-based LLM chatbot, a Code Completion VSCode Extension, and deploying LLM to edge devices like Raspberry Pi. By the time you’re done reading, you’ll be ready to start developing LLMs and effectively incorporating them into software.

About the reader

For data scientists and ML engineers, who know Python and the basics of Kubernetes and cloud deployment.

About the author

Christopher Brousseau is a Staff MLE at JPMorganChase with a linguistics and localization background. He specializes in linguistically-informed NLP, especially with an international focus and has led successful ML and Data product initiatives at both startups and Fortune 500s.

Matt Sharp is an engineer, former data scientist, and seasoned technology leader in MLOps. Has led many successful data initiatives for both startups and top-tier tech companies alike. Matt specializes in deploying, managing, and scaling machine learning models in production, regardless of what that production setting looks like.