Andy Peng, Alex Strick van Linschoten, Duarte O Carmo

DeepSeek in Practice

From basics to fine-tuning, distillation, agent design, and prompt engineering of open source LLM

• Broschiertes Buch

Produktbeschreibung

Gain hands-on experience building, fine-tuning, and deploying GenAI applications using DeepSeek Key Features: - Explore DeepSeek's architecture, training data, and reasoning capabilities - Build agents, fine-tune with distillation, and deploy with CI/CD pipelines - Apply DeepSeek to real-world use cases like coding, ideation, and legal analysis - Purchase of the print or Kindle book includes a free PDF eBook Book Description: Learn how to build, fine-tune, and deploy AI systems using DeepSeek, one of the most influential open-source large language models available today. This book guides you through real-world DeepSeek applications-from understanding its core architecture and training foundations to developing reasoning agents and deploying production-ready systems. Starting with a concise synthesis of DeepSeek's research, breakthroughs, and open-source philosophy, you'll progress to hands-on projects including prompt engineering, workflow design, and rationale distillation. Through detailed case studies-ranging from document understanding to legal clause analysis-you'll see how to use DeepSeek in high-value GenAI scenarios. You'll also learn to build sophisticated agent workflows and prepare data for fine-tuning. By the end of the book, you'll have the skills to integrate DeepSeek into local deployments, cloud CI/CD pipelines, and custom LLMOps environments. Written by experts with deep knowledge of open-source LLMs and deployment ecosystems, this book is your comprehensive guide to DeepSeek's capabilities and implementation. What You Will Learn: - Discover DeepSeek's unique traits in the LLM landscape - Compare DeepSeek's multimodal features with leading models - Consume DeepSeek via the official API, Ollama, and llama.cpp - Use DeepSeek for coding, document understanding, and creative ideation - Integrate DeepSeek with third-party platforms like OpenRouter and Cloudflare - Distill and deploy DeepSeek models into production environments - Identify when and where to use DeepSeek - Understand DeepSeek's open philosophy Who this book is for: AI engineers, developers, and builders working with open-source LLMs who want to integrate DeepSeek into GenAI applications, agent workflows, or deployment pipelines. Readers should have hands-on experience with Python, APIs, and tools like Ollama or llama.cpp, and a solid understanding of machine learning concepts. Table of Contents - What is DeepSeek? - Deep Dive into DeepSeek - Prompting DeepSeek - Using DeepSeek: Case Studies - Building with DeepSeek - Agents with DeepSeek - DeepSeek-Driven Fine-Tuning of Gemma 3 for Legal Reasoning - Deploying DeepSeek Models

Produktdetails

• Verlag: Packt Publishing
• Seitenzahl: 478
• Erscheinungstermin: 21. November 2025
• Englisch
• Abmessung: 235mm x 191mm x 26mm
• Gewicht: 885g
• ISBN-13: 9781806020850
• ISBN-10: 1806020858
• Artikelnr.: 75952305

Autorenporträt

Andy Peng is a Senior Engineer at Amazon. He specializes in large language model inference optimization and evaluation for models like DeepSeek, Qwen, and Claude. His work spans AWS Bedrock, SageMaker, Amazon S3, AWS Fargate, AWS App Runner, Alexa Health & Wellness, and fintech. A NeurIPS 2025 Chair and program committee member for ICML, ICLR, KDD, and NeurIPS, he contributes to CNCF and the Linux Foundation, mentors at the University of Washington, and serves as a Resident Expert at the AI2 Incubator.