Hands-On Large Language Models 动手操作大型语言模型 大神搞的中英翻译版,非常不错 (Jay Alammar, Maarten Grootendorst) (Z-Library)

【One-Line Pitch】 AI has acquired startling new language capabilities in just the past few years. Driven by the rapid advances in deep … 【Book Arc】 - **Opening (~0%–12%)**: Driven by the rapid advances in deep learning, language AI systems are able to write and understand text better than ever before.; 在 GenAI 革命的核心，这本不可或缺的指南巧妙地平衡了理论与实践，引领读者穿越大型语言模型的广阔领域，为他们在 AI 领域带来即时和变革性的影响提供所需的知识。 - **Early (~12%–35%)**: itecture, we will explore the history and evolution of LLMs.; ction between representation and generative language models. - **Middle (~35%–65%)**: For more information, visit https://oreilly.com .; 我非常感谢我的家人给予我坚定不移的支持和灵感。我想特别感谢我的父母阿卜杜拉和米沙埃尔，以及我的阿姨胡萨和阿尔乔哈拉。 - **Late (~65%–88%)**: emantic nature, or meaning, of text.; good way to translate human language into computer language. - **Ending (~88%–100%)**: n, which is used as the representation for the entire input.; is generally less compute-intensive and requires less data. 【Key Takeaways】 - **Driven by the rapid ad…** (Opening): Driven by the rapid advances in deep learning, language AI systems are able to write and understand text better than ever before. - **在 GenAI 革命的核心** (Opening): 在 GenAI 革命的核心，这本不可或缺的指南巧妙地平衡了理论与实践，引领读者穿越大型语言模型的广阔领域，为他们在 AI 领域带来即时和变革性的影响提供所需的知识。 - **版权所有 2024 Jay Alammar…** (Opening): 版权所有 2024 Jay Alammar 和 Maarten Pieter Grootendorst。保留所有权利。 - **itecture** (Early): itecture, we will explore the history and evolution of LLMs. - **ction between represen…** (Early): ction between representation and generative language models. - **模型进行语义搜索（见第 6 章）** (Early): 模型进行语义搜索（见第 6 章），生成文本（见第 7 章和第 8 章），以及扩展文本生成功能至视觉领域（见第 9 章）。 【Reading Tips】 - Use Passage locations below to jump into the text and set reading anchors - If this is a brief outline, click Regenerate (top right) for a synthesized guide 【Coverage Limits】 Compressed outline without the model (~33 index chunks). Full structured guide needs AI available.