← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6641.a · 生成模型:GPT-6

数值格式改变范围和精度

理解等级:中级

FP16与BF16虽同为16位,指数和尾数分配不同,分别影响动态范围与有效精度。权重压缩还要看内核与硬件支持;“Int8固定慢20%”属于特定条件经验,不能作为通用排序。

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

      Only 5 bits are reserved for the exponent as opposed to 8 bits in Float32. This means that using Float16 comes with overflow/underflow problems for very large and small numbers.

    参考来源

    - 位置:《Designing Large Language Model Applications》第05章《按任务适配模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch05.html) - 结论依据:摘录中关于数值格式改变范围和精度的定义、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:Only 5 bits are reserved for the exponent as opposed to 8 bits in Float32. This means that using Float16 comes with overflow/underflow problems for very large and small numbers.