……Chip Huyen 写的《设计机器学习系统：构建面向生产环境的应用的迭代流程》（Designing Machine Learning Systems）。2) Chip Huyen 的《AI 工程化：利用基础模型构建应用》（AI Engineering，这是一本刚出的新书）。3) David Foster 的《生成式深度学习：教机器去画画、写作、作曲和游戏》（Generative Deep Learning）。4) Bouchard 和 Peters 合著的《构建生产级大语言模型：通过 Prompt 工程、微调和 RAG 提升 LLM 能力与可靠性》（Building LLMs for Production）。
…Learning Systems: An Iterative Process for Production-Ready Applications by Chip Huyen. 2) AI Engineering: Building Applications with Foundation Models by Chip Huyen (this is a very recent book). 3) Generative Deep Learning: Teaching Machines To Paint, Write, Compose, and Play by David Foster. 4) Building LLMs for Production: Enhancing LLM Abilities and Reliability with Prompting, Fine-Tuning, and RAG by Bouchard & Peters.
…I've seen would be something like one of these: https://www.amazon.com/Transformers-Natural-Language-Process... https://www.amazon.com/Natural-Language-Processing-Transform... https://www.amazon.com/Generative-Deep-Learning-Teaching-Mac... I wish I could give you a detailed review of all of those, but sadly while I have all three, I've been too slammed with other stuff to make much progress on any of them. :-( And while…
……tokenizer，但那不是讨论的重点。问题在于 tokenizer 会不会整出训练词表之外的词。Word tokenizer 不会，但 character tokenizer 会。出处：David Foster 写的《生成式深度学习》（Generative Deep Learning）第二版，2023 年出版。摘自第 134 页的“Tokenization”一节：“如果使用 word token：……将永远无法预测训练词表之外的词汇。”“如果使用 character……
…tokenizers, but that is not the topic of discussion. The question is will the tokenizer come up with words not in the training vocabulary. Word tokenizers don’t, but character tokenizers do. Source: Generative Deep Learning by David Foster, 2nd edition, published in 2023. From “Tokenization” on page 134. “If you use word tokens: …. willnever be able to predict words outside of the training vocabulary.” "If you use character…
出处：David Foster 写的《生成式深度学习》（Generative Deep Learning）第二版，2023 年出版。摘自第 134 页的“Tokenization”一节：“如果使用 word token：……将永远无法预测训练词表之外的词汇。”“如果使用 character……
Source: Generative Deep Learning by David Foster, 2nd edition, published in 2023. From “Tokenization” on page 134. “If you use word tokens: …. willnever be able to predict words outside of the training vocabulary.” "If you use character…
……当然前提是你找到了契合自己需求的书。我认识一些人，除非确定自己能从头读到尾，否则连翻都不愿意翻开，我觉得这种想法挺荒谬的。我刚订了 O'Reilly 出的《生成式深度学习》（Generative Deep Learning），希望能从中有所收获；哪怕我以后职业生涯里只能用上其中的寥寥几段代码或技巧，这钱花得就算值了。再不济，摆在书架上也挺好看的。
…found the right one for your needs, of course. I know some people who won't open a book unless they know they can read the whole thing, which I think is a ludicrous attitude. I did just order O'Reilly's Generative Deep Learning book, and am hoping to get something out of that, and if I only retain a handful of snippets to use in my career, that is profitable for me. The least I can count on is that it will look nice on my shelf.
……Chip Huyen 写的《设计机器学习系统：构建面向生产环境的应用的迭代流程》（Designing Machine Learning Systems）。2) Chip Huyen 的《AI 工程化：利用基础模型构建应用》（AI Engineering，这是一本刚出的新书）。3) David Foster 的《生成式深度学习：教机器去画画、写作、作曲和游戏》（Generative Deep Learning）。4) Bouchard 和 Peters 合著的《构建生产级大语言模型：通过 Prompt 工程、微调和 RAG 提升 LLM 能力与可靠性》（Building LLMs for Production）。
…Learning Systems: An Iterative Process for Production-Ready Applications by Chip Huyen. 2) AI Engineering: Building Applications with Foundation Models by Chip Huyen (this is a very recent book). 3) Generative Deep Learning: Teaching Machines To Paint, Write, Compose, and Play by David Foster. 4) Building LLMs for Production: Enhancing LLM Abilities and Reliability with Prompting, Fine-Tuning, and RAG by Bouchard & Peters.
……我见过的应该类似于这几本：https://www.amazon.com/Transformers-Natural-Language-Process... https://www.amazon.com/Natural-Language-Processing-Transform... https://www.amazon.com/Generative-Deep-Learning-Teaching-Mac... 真希望能给你写一份详细的书评，但遗憾的是，虽然这三本我都有，可手头事情实在太多太忙，哪一本都没看多少。:-( 虽说……
…I've seen would be something like one of these: https://www.amazon.com/Transformers-Natural-Language-Process... https://www.amazon.com/Natural-Language-Processing-Transform... https://www.amazon.com/Generative-Deep-Learning-Teaching-Mac... I wish I could give you a detailed review of all of those, but sadly while I have all three, I've been too slammed with other stuff to make much progress on any of them. :-( And while…
……tokenizer，但那不是讨论的重点。问题在于 tokenizer 会不会整出训练词表之外的词。Word tokenizer 不会，但 character tokenizer 会。出处：David Foster 写的《生成式深度学习》（Generative Deep Learning）第二版，2023 年出版。摘自第 134 页的“Tokenization”一节：“如果使用 word token：……将永远无法预测训练词表之外的词汇。”“如果使用 character……
…tokenizers, but that is not the topic of discussion. The question is will the tokenizer come up with words not in the training vocabulary. Word tokenizers don’t, but character tokenizers do. Source: Generative Deep Learning by David Foster, 2nd edition, published in 2023. From “Tokenization” on page 134. “If you use word tokens: …. willnever be able to predict words outside of the training vocabulary.” "If you use character…
出处：David Foster 写的《生成式深度学习》（Generative Deep Learning）第二版，2023 年出版。摘自第 134 页的“Tokenization”一节：“如果使用 word token：……将永远无法预测训练词表之外的词汇。”“如果使用 character……
Source: Generative Deep Learning by David Foster, 2nd edition, published in 2023. From “Tokenization” on page 134. “If you use word tokens: …. willnever be able to predict words outside of the training vocabulary.” "If you use character…
……当然前提是你找到了契合自己需求的书。我认识一些人，除非确定自己能从头读到尾，否则连翻都不愿意翻开，我觉得这种想法挺荒谬的。我刚订了 O'Reilly 出的《生成式深度学习》（Generative Deep Learning），希望能从中有所收获；哪怕我以后职业生涯里只能用上其中的寥寥几段代码或技巧，这钱花得就算值了。再不济，摆在书架上也挺好看的。
…found the right one for your needs, of course. I know some people who won't open a book unless they know they can read the whole thing, which I think is a ludicrous attitude. I did just order O'Reilly's Generative Deep Learning book, and am hoping to get something out of that, and if I only retain a handful of snippets to use in my career, that is profitable for me. The least I can count on is that it will look nice on my shelf.