ODBIERZ TWÓJ BONUS :: »

DeepSeek Essentials. Learn to build models and apply distillation effectively with DeepSeek Andy Peng, Alex Strick van Linschote, Duarte Carmo

Język publikacji: angielski
DeepSeek Essentials. Learn to build models and apply distillation effectively with DeepSeek Andy Peng, Alex Strick van Linschote, Duarte Carmo - okladka książki

DeepSeek Essentials. Learn to build models and apply distillation effectively with DeepSeek Andy Peng, Alex Strick van Linschote, Duarte Carmo - okladka książki

Autorzy:
Andy Peng, Alex Strick van Linschote, Duarte Carmo
Serie wydawnicze:
Hands-on
Ocena:
DeepSeek has emerged as a promising open-source language model, with capabilities that rival leading proprietary systems like ChatGPT. But what makes it special, and how can IT professionals and AI practitioners put it to use? DeepSeek Essentials takes a practical, no-nonsense approach to helping you build with DeepSeek models in real-world scenarios.
You’ll explore DeepSeek’s origin, architecture, and multimodal strengths to grasp what sets it apart from ChatGPT and other LLMs and understand its current state, strengths, and gaps to make smart, informed choices about when and how to use it. With concrete examples in coding, document analysis, and ideation, you’ll build confidence using DeepSeek. You’ll also learn to work with cloud APIs such as OpenRouter and Cloudflare or run DeepSeek locally using tools like Ollama and llama.cpp.
The concluding chapters focus on GenAI-powered applications, covering agent development and workflow design. You’ll learn to distill and extend models for custom needs, enabling fast, adaptive solutions across enterprises, startups, or research.
By the end of this book, you’ll have gained the clarity and skills to build effectively with DeepSeek, whether it be evaluating AI tools or developing next-gen apps.

Wybrane bestsellery

O autorach książki

Andy Peng, a builder with curiosity, motivated by research and product innovation. He has led both 0-to-1 and 10x scaling across areas like LLM inference and optimizations on AWS Bedrock, state-of-the-art models (Claude, LLaMA, DeepSeek), foundational data service (Amazon S3), serverless compute (App Runner, Fargate), conversational AI (Alexa Healthcare), fintech, etc. He is committed to research and open-source, serving on program committees for ICML, NeurIPS, and NPOs like the Linux Foundation and CNCF (as Ambassador). He is also a mentor and guest lecturer at the University of Washington.
Alex Strick van Linschoten is a Machine Learning Engineer at ZenML. He led the development of the LLMOps database, a comprehensive collection of over 800 case studies examining LLMOps and GenAI implementations in production environments. His work focuses on bridging the gap between machine learning research and production deployment, particularly for the LLMOps space. He transitioned to software engineering after earning a PhD in History and spending 15 years living and working as a historian and researcher in Afghanistan. He has authored, edited and translate several books based on his historical research and is based in Delft, the Netherlands.
Duarte Carmo is a technologist, born and raised in sunny Lisbon, now based in Copenhagen. His work lies in the intersection of Machine Learning & AI, Data, Software, and People. He is in love with Technology, and how it can improve people's lives.
In the past, he has worked in Consumer Electronics, Public Institutions, Big Three Management Consulting, and YC-backed startups. The common thread? Solving hard problems end-to-end.
His work is greatly shaped by his background and education. He has studied at the Superior Technical Institute of Lisbon, the Beijing Institute of Technology, and the Technical University of Denmark.
When he is not solving hard problems, you can find him geeking out about new gadgets, writing code, reading, taking photos, or running.

Zobacz pozostałe książki z serii Hands-on

Packt Publishing - inne książki

Zamknij

Przenieś na półkę
Dodano produkt na półkę
Usunięto produkt z półki
Przeniesiono produkt do archiwum
Przeniesiono produkt do biblioteki

Zamknij

Wybierz metodę płatności

Sposób płatności