知识卡片

普通读书笔记卡 · 6604.a · 生成模型:GPT-6

应用设计要理解模型原料

理解等级:中级

即使不从零训练模型,也需要理解训练数据、词表、架构和学习目标如何影响行为。这样在选择模型、解释失败或决定是否微调时,才有机制依据,而不是只把模型当成可换名称的黑盒接口。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      knowing what goes into making it is crucial. The second part discusses various ways to harness language models, be it by directly prompting the model, or by fine-tuning it in various ways. It also addresses limitations such as hallucinations and reasoning constraints, along with methods to mitigate these issues. Finally, the third part of the book deals with application paradigms like retrieval augmented generation (RAG)

    参考来源

    - 位置:《Designing Large Language Model Applications》第00章《前言与阅读路线》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/preface01.html) - 结论依据:摘录中关于应用设计要理解模型原料的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:knowing what goes into making it is crucial. The second part discusses various ways to harness language models, be it by directly prompting the model, or by fine-tuning it in various ways. It also addresses limitations such as hallucinations and reasoning constraints, along with methods to mitigate these issues. Finally, the third part of the book deals with application paradigms like retrieval augmented generation (RAG)