February 2025
Intermediate
376 pages
9h 25m
Japanese
Content preview from 仕組みからわかる大規模言語モデル 生成AI時代のソフトウェア開発入門
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
図1.3.9 にマスク付きマルチヘッド注意機構の構成を示します。マスク付きマルチヘッド注
意機構は、
n#D
model
の入力埋め込み行列を入力とし、
n#D
model
の出力埋め込み行列を出力
します。
n#D
model
の入力埋め込み行列は、
h
個（
h
はヘッド数）のマスク付き注意機構に入力
として与えられます。各マスク付き注意機構の出力は、
n#D
head
の行列となります。ここで、
D
head
=
D
model
/
h
です。マスク付き注意機構の出力は再び連結され、
n#D
model
の行列として出
力されます。そして線形変換を行い、
n#D
model
の出力埋め込み行列を得ます。線形変換は
D
model
#D
model
の重み行列
W
O
を用いて行われます。
このマルチヘッド注意機構の出力を式で表すと、次のようになります。
MultiHead
(X)
=Concat
(head
1
, head
2
, g, head
h
)W
O
ここで、
X
は入力埋め込み行列、各
head
i
はマスク付き注意機構の出力、
W
O
はこれらの出
力を結合した後に適用される重み行列、Concatは行列の連結を表します。
h
図1.3.9
注意機構の意味
注意機構は、Transformerの中で特に重要な機能の一つです。実際、Transformer が提案さ
れた論文のタイトル「Attention Is All
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.