May 2025
Intermediate to advanced
382 pages
10h 33m
Chinese
Content preview from 图解大模型 : 生成式AI 原理与实战
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
220
｜
第
9
章
我们已见证
LLM
展现出包括泛化推理、数学运算及语言理解在内的涌现能力。随着模型
规模的扩大与智能水平的提升，其技能图谱将持续拓展
1
。
接收并理解多模态输入的能力，或将进一步释放模型的潜能。事实上，语言并非孤立存在
的，肢体动作、面部表情、语调变化等非语言要素，均能增强口语表达。这一原理同样适
用于
LLM
。若赋予其理解多模态信息的能力，其功能边界将得以拓展，从而能够解决更多
新型问题。
本章将探讨具备多模态能力的
LLM
及其实际应用场景。首先解析如何通过改进原始
Transformer
技术，将图像转换为数值表示。随后展示如何扩展
LLM
架构，使其具备视觉
任务处理能力。
9.1
视觉
Transformer
在本书各章节中，从分类、聚类到搜索生成，我们见证了基于
Transformer
的模型在语言
建模任务中的卓越表现。自然，研究者开始尝试将
Transformer
的成功经验迁移至计算机
视觉领域。
由此诞生的视觉
Transformer
（
Vision Transformer
，
ViT
），在图像识别任务中展现出超越传统
卷积神经网络（
convolutional neural network
，
CNN
）的性能
2
。与原始
Transformer
类似，
ViT
的核心功能是将非结构化的图像数据转换为可用于分类等任务的数值表示，如图
9-2
所示。
Transformer
视觉
Transformer
(ViT)
输入
特征
输出
预测
You have been
selected to receive
1.4 million dollars! ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.