知识卡片
文本蒸馏与软目标蒸馏有别
推理蒸馏可把较强模型生成的指令与解答当作监督示例,让另一模型学习。传统蒸馏也可能使用教师的分数或概率分布。两种监督信息不同,模仿文本风格不保证获得教师全部能力,且学生不必在所有方案中都更小。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 理解推理模型
原书出处 · 1 处
- · 查看原书依据
this differs slightly from traditional knowledge distillation in deep learning, where a smaller ("student") model typically learns from both the outputs and the logits produced by a larger ("teacher") model. This topic is discussed further in chapter 8.
参考来源
- 位置:《Build a Reasoning Model (From Scratch)》第01章《理解推理模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Build a Reasoning Model (From Scratch)/_epub-src/OEBPS/Text/chapter-1.html)
- 结论依据:摘录中关于文本蒸馏与软目标蒸馏有别的定义、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:this differs slightly from traditional knowledge distillation in deep learning, where a smaller ("student") model typically learns from both the outputs and the logits produced by a larger ("teacher") model. This topic is discussed further in chapter 8.