Llms in Production: From Language Models to Successful Products (Paperback)
暫譯: 生產中的大型語言模型：從語言模型到成功產品

Brousseau, Christopher, Sharp, Matt

Llms in Production: From Language Models to Successful Products (Paperback)
  • 出版商: Manning
  • 出版日期: 2025-02-11
  • 售價: $2,100
  • 貴賓價: 9.5 折 $1,995
  • 語言: 英文
  • 頁數: 456
  • 裝訂: Quality Paper - also called trade paper
  • ISBN: 1633437205
  • ISBN-13: 9781633437203
  • 相關分類: Large language model

    • 立即出貨 (庫存 < 4)

買這商品的人也買了...

LLM 大語言模型-2書75折 詳見活動內容 »

相關主題

商品描述

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.

商品描述(中文翻譯)

學習如何安全且高效地將基於大型語言模型的應用程式投入生產。

大型語言模型（Large Language Models, LLMs）是像 ChatGPT、LLAMA 和 Bard 等 AI 工具的基礎。本書提供了清晰且充滿範例的解釋，說明 LLMs 的運作方式、如何與它們互動，以及如何將 LLMs 整合到自己的應用程式中。在 LLMs in Production 中，您將：


  • 掌握 LLMs 的基本原理及其背後的技術

  • 評估何時使用現成的 LLM 以及何時構建自己的 LLM

  • 有效擴展機器學習平台以滿足 LLMs 的需求

  • 訓練 LLM 基礎模型並微調現有的 LLM

  • 使用複雜架構（如 RLHF）將 LLM 部署到雲端和邊緣設備

  • 構建應用程式，利用 LLMs 的優勢，同時減輕其弱點



LLMs in Production 提供了關於 LLMs 的 MLOps 交付的重要見解。您將學習如何將這些強大的 AI 模型運用於聊天機器人、編碼助手等。了解 LLMs 與傳統軟體和機器學習的不同之處，發現實驗室外工作的最佳實踐，並透過經驗豐富的建議避免常見的陷阱。

購買印刷版書籍可獲得 Manning Publications 提供的免費 PDF 和 ePub 格式電子書。

關於本書

LLMs in Production 是您有效指導 LLMs 進入生產使用的全面指南。它帶您了解 LLM 的整個生命週期，從最初的概念到創建和微調，再到部署。您將發現如何有效準備 LLM 數據集、成本效益的訓練技術（如 LORA 和 RLHF），以及如何根據行業基準評估您的模型。

學習如何正確建立部署基礎設施並解決常見挑戰，如再訓練和負載測試。最後，您將親手操作三個令人興奮的範例專案：一個基於雲端的 LLM 聊天機器人、一個代碼補全的 VSCode 擴展，以及將 LLM 部署到邊緣設備（如 Raspberry Pi）。當您讀完這本書時，您將準備好開始開發 LLM 並有效地將其整合到軟體中。

關於讀者

適合已知 Python 及 Kubernetes 和雲端部署基礎知識的數據科學家和機器學習工程師。

關於作者

Christopher Brousseau 是 JPMorganChase 的資深機器學習工程師，擁有語言學和本地化背景。他專注於語言學知識驅動的自然語言處理（NLP），特別是具有國際焦點的 NLP，並在初創公司和《財富》500 強企業中領導成功的機器學習和數據產品計劃。

Matt Sharp 是一名工程師、前數據科學家和資深 MLOps 技術領導者。他為初創公司和頂尖科技公司領導了許多成功的數據計劃。Matt 專注於在生產環境中部署、管理和擴展機器學習模型，無論該生產環境的樣貌如何。

作者簡介

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.

作者簡介(中文翻譯)

克里斯多福·布魯索（Christopher Brousseau）是摩根大通（JPMorgan Chase）的資深機器學習工程師（Staff MLE），擁有語言學和本地化的背景。他專注於語言學知識驅動的自然語言處理（NLP），特別是具有國際視野的應用，並在初創公司和《財富》500 強企業中領導過成功的機器學習和數據產品計劃。

馬特·夏普（Matt Sharp）是一位工程師、前數據科學家以及經驗豐富的 MLOps 技術領導者。他為初創公司和頂尖科技公司領導了許多成功的數據計劃。馬特專注於在生產環境中部署、管理和擴展機器學習模型，無論該生產環境的具體情況如何。

類似商品