Unlimited access to the largest independent learning library in Tech!

Try FREE for 7 days. Only $19.99/month after. Cancel anytime!

Your Suggested Titles

Find content based on your preferences and activity, edit your preferences here

LLM Engineer's Handbook

Read now

4.8

By Paul Iusztin
October 2024 | 522 pages

Build and refine LLMs step by step, covering data preparation, RAG, and fine-tuning

Learn essential skills for deploying and monitoring LLMs, ensuring optimal performance in production

Utilize preference alignment, evaluation, and inference optimization to enhance performance and adaptability of your LLM applications

Understanding the LLM Twin Concept and Architecture

Understanding the LLM Twin Concept and Architecture Understanding the LLM Twin concept Planning the MVP of the LLM Twin product Building ML systems with feature/training/inference pipelines Designing the system architecture of the LLM Twin Summary References

Tooling and Installation

Tooling and Installation Python ecosystem and project installation MLOps and LLMOps tooling Databases for storing unstructured and vector data Preparing for AWS Summary References

Data Engineering

Data Engineering Designing the LLM Twin’s data collection pipeline Gathering raw data into the data warehouse Summary References

RAG Feature Pipeline

RAG Feature Pipeline Understanding RAG An overview of advanced RAG Exploring the LLM Twin’s RAG feature pipeline architecture Implementing the LLM Twin’s RAG feature pipeline Summary References

Supervised Fine-Tuning

Supervised Fine-Tuning Creating an instruction dataset Creating our own instruction dataset Exploring SFT and its techniques Fine-tuning in practice Summary References

Fine-Tuning with Preference Alignment

Fine-Tuning with Preference Alignment Understanding preference datasets Creating our own preference dataset Preference alignment Implementing DPO Summary References

Evaluating LLMs

Evaluating LLMs Model evaluation RAG evaluation Evaluating TwinLlama-3.1-8B Summary References

Inference Optimization

Inference Optimization Model optimization strategies Model parallelism Model quantization Summary References

RAG Inference Pipeline

RAG Inference Pipeline Understanding the LLM Twin’s RAG inference pipeline Exploring the LLM Twin’s advanced RAG techniques Implementing the LLM Twin’s RAG inference pipeline Summary References

Inference Pipeline Deployment

Inference Pipeline Deployment Criteria for choosing deployment types Understanding inference deployment types Monolithic versus microservices architecture in model serving Exploring the LLM Twin’s inference pipeline deployment strategy Deploying the LLM Twin service Autoscaling capabilities to handle spikes in usage Summary References

MLOps and LLMOps

MLOps and LLMOps The path to LLMOps: Understanding its roots in DevOps and MLOps Deploying the LLM Twin’s pipelines to the cloud Adding LLMOps to the LLM Twin Summary References

Other Books You May Enjoy

Index

Read table of contents

Suggested Titles

4.8

LLM Engineer's Handbook

Paul Iusztin and 1 more

Oct-24

4.9

Python Machine Learning By Example

Yuxi (Hayden) Liu

Jul-24

C# 13 and .NET 9 – Modern Cross-Platform Development Fundamentals

Mark J. Price

Nov-24

Expert reading lists

If you want to advance your tech knowledge but don't know where to start, explore Expert Reading Lists comprising our best titles on popular technologies grouped together by the Packt community.

View All

Expert Reading List

Learning C# by Developing Games with Unity

Getting Started with Game Development

Start your journey in game development by building games using beginner-friendly tools. Learn programming language, explore design basics, and create your first game projects from scratch.

Created: Apr-25

Modern Generative AI with ChatGPT and OpenAI Models

Prompt Engineering For Everyone with ChatGPT and GPT-4

Getting Started with ChatGPT

Stay ahead of the game and start unlocking the full potential of OpenAI and ChatGPT today.

Created: Mar-25

Embedded Linux Development Using Yocto Project

Mastering Linux Device Driver Development

Embedded Linux and Driver Development

Deep dive into Linux for embedded systems—from user-space tools to kernel-space driver development. Ideal for developers aiming to build performance-critical, low-level applications.

Created: Apr-25

Build Stunning Real-time VFX with Unreal Engine 5

Photorealistic Materials and Textures in Blender Cycles

Visual Effects and Shader Programming

Add stunning visuals with post-processing, shaders, and VFX. Create atmospheric worlds, glowing powers, and photoreal effects using Unity, Unreal, and Blender.

Created: Apr-25