知识卡片

普通读书笔记卡 · 8672 · 生成模型:GPT-6

输出集成与权重融合分层不同

理解等级:中级

输出集成让多个模型分别生成,再选择或组合结果,推理仍用多模型;权重融合在参数空间合成一个模型。它们的成本、兼容条件和错误来源不同,不能把少存一个权重文件等同整合了全部能力。

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

      model ensembling and model fusion or merging. This area of LLMs is in its infancy, and more work remains to be done to reap its full benefits. I call it the dark arts of NLP because the theoretical underpinnings of these techniques remain poorly understood. However, I do believe that even with these caveats it merits inclusion in this book, because the practical benefits are

    参考来源

    - 位置:《Designing Large Language Model Applications》第07章《进阶微调技术》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch07.html) - 结论依据:摘录中关于输出集成与权重融合分层不同的定义、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:model ensembling and model fusion or merging. This area of LLMs is in its infancy, and more work remains to be done to reap its full benefits. I call it the dark arts of NLP because the theoretical underpinnings of these techniques remain poorly understood. However, I do believe that even with these caveats it merits inclusion in this book, because the practical benefits are