原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
and so on. We can make all these predictions at once with a single matrix multiply (figure 26.18): Figure 26.18: Masked attention to make multiple causal predictions at once. Black cells are masked; they are filled with zeros. This way, one forward pass makes N predictions rather than one prediction. This is equivalent to doing a single next token prediction N times, but it all
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c026.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8