國立高雄大學圖資館 |

登入

回首頁

LLMs in production :from language models to successful products /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	LLMs in production :Christopher Brousseau, Matthew Sharp ; foreword by Joe Reis.
其他題名:	from language models to successful products /
其他題名:	Large Language Models in production
作者:	Brousseau, Christopher,
其他作者:	Sharp, Matt,
出版者:	Shelter Island, NY :Manning Publications Co.,c2025.
面頁冊數:	xx, 432 p. :ill. ;24 cm.
附註:	Includes index.
標題:	Computational linguistics.
ISBN:	9781633437203 (pbk.) :

LLMs in production :from language models to successful products /
Brousseau, Christopher,

LLMs in production :from language models to successful products /Large Language Models in productionChristopher Brousseau, Matthew Sharp ; foreword by Joe Reis. - Shelter Island, NY :Manning Publications Co.,c2025. - xx, 432 p. :ill. ;24 cm.

Includes index.

Words' awakening: why large language models have captured attention -- Large language models: a deep dive into language modeling -- Large language model operations: building a platform for LLMs -- Data engineering for large language models: setting up for success -- Training large language models: how to generate the generator -- Large language model services: a practical guide -- Prompt engineering: becoming an LLM whisperer -- Large language model applications: building an interactive experience -- Creating an LLM project: reimplementing Llama 3 -- Creating a coding copilot project: this would have helped you earlier -- Deploying an LLM on a Raspberry Pi: How low can you go? -- Production, an ever-changing landscape: Things are just getting started.

Most business software is developed and improved iteratively, and can change significantly even after deployment. By contrast, because LLMs are expensive to create and difficult to modify, they require meticulous upfront planning, exacting data standards, and carefully-executed technical implementation. Integrating LLMs into production products impacts every aspect of your operations plan, including the application lifecycle, data pipeline, compute cost, security, and more. Get it wrong, and you may have a costly failure on your hands. LLMs in production teaches you how to develop an LLMOps plan that can take an AI app smoothly from design to delivery. You'll learn techniques for preparing an LLM dataset, cost-efficient training hacks like LORA and RLHF, and industry benchmarks for model evaluation. Along the way, you'll put your new skills to use in three exciting example projects: creating and training a custom LLM, building a VSCode AI coding extension, and deploying a small model to a Raspberry Pi.

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

ISBN: 9781633437203 (pbk.) :NT$1742Subjects--Topical Terms:

181250
Computational linguistics.

LC Class. No.: Q335

Dewey Class. No.: 006.35

LLMs in production :from language models to successful products /
LDR:02615cam a2200241 a 4500 001 675795
003 OCoLC
005 20250620035201.0
008 250818s2025 nyua 001 0 eng d
020 $a 9781633437203 (pbk.) : $c NT$1742
020 $a 1633437205 (pbk.)
035 $a (OCoLC)1442731345
035 $a on1442731345
040 $a YDX $b eng $c YDX $d OCLCO $d JRZ $d OCLCO $d BDX
050 4 $a Q335
082 0 4 $a 006.35 $2 23
100 1 $a Brousseau, Christopher, $e author. $3 989562
245 1 0 $a LLMs in production : $b from language models to successful products / $c Christopher Brousseau, Matthew Sharp ; foreword by Joe Reis.
246 3 $a Large Language Models in production
260 $a Shelter Island, NY : $b Manning Publications Co., $c c2025.
300 $a xx, 432 p. : $b ill. ; $c 24 cm.
500 $a Includes index.
505 0 $a Words' awakening: why large language models have captured attention -- Large language models: a deep dive into language modeling -- Large language model operations: building a platform for LLMs -- Data engineering for large language models: setting up for success -- Training large language models: how to generate the generator -- Large language model services: a practical guide -- Prompt engineering: becoming an LLM whisperer -- Large language model applications: building an interactive experience -- Creating an LLM project: reimplementing Llama 3 -- Creating a coding copilot project: this would have helped you earlier -- Deploying an LLM on a Raspberry Pi: How low can you go? -- Production, an ever-changing landscape: Things are just getting started.
520 $a Most business software is developed and improved iteratively, and can change significantly even after deployment. By contrast, because LLMs are expensive to create and difficult to modify, they require meticulous upfront planning, exacting data standards, and carefully-executed technical implementation. Integrating LLMs into production products impacts every aspect of your operations plan, including the application lifecycle, data pipeline, compute cost, security, and more. Get it wrong, and you may have a costly failure on your hands. LLMs in production teaches you how to develop an LLMOps plan that can take an AI app smoothly from design to delivery. You'll learn techniques for preparing an LLM dataset, cost-efficient training hacks like LORA and RLHF, and industry benchmarks for model evaluation. Along the way, you'll put your new skills to use in three exciting example projects: creating and training a custom LLM, building a VSCode AI coding extension, and deploying a small model to a Raspberry Pi.
521 $a For data scientists and ML engineers who know Python and the basics of cloud deployment
650 0 $a Computational linguistics. $3 181250
650 0 $a Natural language processing (Computer science) $3 200539
650 0 $a Artificial intelligence. $3 194058
650 0 $a Chatbots. $3 970198
650 0 $a Machine translating. $3 180536
700 1 $a Sharp, Matt, $c (Engineer), $e author. $3 989563
700 1 $a Reis, Joe $q (Joseph), $e writer of foreword. $3 989564