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.
は、
i
番目のトークンのクエリベクトルと
j
番目のトークンのキーベクトルの内積の結果です。
この行列は、トークン間の関連性を表す行列となります。
この行列を得るには、クエリ行列
Q
とキー行列
K
の行列積を利用します。
Q
と
K
は両方とも
n#D
head
の行列ですから、両者をこのまま掛け合わせることはできません。行列の掛け算で
は、掛ける行列の列数と掛けられる行列の行数が一致している必要があります。ここで求めた
い行列は
n# n
の行列のため、
n#D
head
の行列と
D
head
# n
の行列を掛け合わせればよいこと
がわかります。そこで、
Q
と
K
の積を取る前に、
K
の行と列を入れ替えた転置行列
K
T
を用意
します。この転置行列
K
T
は、
D
head
# n
の行列です。これで両者を掛け合わせることができる
ようになりました。この積を計算すると
n# n
の行列が得られます。この行列
QK
T
の
i
行
j
列
の要素は、
Q
の
i
行目、すなわち
i
番目のトークンのクエリベクトルと、
K
T
の
j
列 目（
K
の
j
行目）、すなわち
j
番目のトークンのキーベクトルの内積の結果です。
次にこの内積を計算した行列
QK
T
をどのように使うかを考えてみます。各要素はクエリベ
クトルとキーベクトルの内積の結果であり、トークン間の関連性を表しています。内積は値が
大きいほど、ベクトル同士の類似度が高いことを意味します。ただし、内積の値はベクトルの
大きさに依存するため、内積の値そのままでは、トークン間の関連性を比較することが難しく
なります。そこで、ソフトマックス関数（1.3.5参照）
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.