dela
3a322aa8dc
Add the ledger schema, class router, lint codes, ingest/build pipeline, and three work-tree examples: align derivation, superfig delegation, and supertensor delegation.
32 lines
916 B
TeX
32 lines
916 B
TeX
\documentclass[border=10pt]{standalone}
|
||
\usepackage[cjk]{supertensor}
|
||
|
||
\stsetrole{q}{stTeal}
|
||
\stsetrole{k}{stOrange}
|
||
\stsetrole{s}{stCoral}
|
||
|
||
\stdim{T}{6}
|
||
\stdim{dh}{3}
|
||
|
||
\begin{document}
|
||
\begin{tikzpicture}
|
||
\ststage{SA}{每头打分：沿 $d_h$ 收缩}
|
||
\strow{rowA}{T}
|
||
\ststack[role=q, bracket=true]{Q}{}{T}{dh}{3}
|
||
\stglyph{mA}{$\times$}
|
||
\ststack[role=k, bracket=true]{KT}{}{dh}{T}{3}
|
||
\stglyph{eA}{$=$}
|
||
\ststack[role=s]{S}{}{T}{T}{3}
|
||
\strowend
|
||
\stcaption{Q}{$\mathbf Q^{(i)}$}{$h\times T\times d_h$}
|
||
\stcaption{KT}{$\mathbf K^{(i)\top}$}{$h\times d_h\times T$}
|
||
\stcaption{S}{$\mathbf S^{(i)}$}{$h\times T\times T$}
|
||
\sttopformula{F}{$S^{(i)}=Q^{(i)}K^{(i)\top}$}
|
||
\stbbox{all}
|
||
\stmeaningbox{mb}{120mm}{all}
|
||
{$T$ 时间；$d_h$ 头维；$h$ 头数画成 stack 深度}
|
||
{$Q/K$ 是 value；$S$ 是 score，不是 mask}
|
||
{沿 $d_h$ 收缩；$K^\top$ 换面，收缩边等长}
|
||
\end{tikzpicture}
|
||
\end{document}
|