原书出处
Designing Large Language Model Applications
32-bit floating point representation, each parameter occupying 4 bytes of storage. Float16 16-bit floating point representation. 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. bfloat16 (BF16) 16-bit floating point representation. Just like Float32, 8 bits are reserved for the exponent, thus alleviating the
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch05.html
EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf