October 2025
Intermediate
424 pages
10h 19m
Korean
Content preview from 실무로 통하는 LLM 애플리케이션 설계
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.
122
1
부
LLM의 구성 요소
연습 문제 ●●●
https
://
oreil
.
ly
/
xwGqK
에서 다운로드할 수 있는 위키백과 데이터셋의 일부를 사용해
BPE
알고리즘을 직접 구현해 보세요. 어휘 크기가
10
,
000
일 때 어떤 토큰들이 생성되며 이들이 인
기 있는 언어 모델의 어휘와 무엇이 다른지 알아보세요. 결과로 얻은 토크나이저를
https
://
oreil
.
ly
/
MqEY9
에서 구할 수 있는 머신러닝 논문 데이터셋과 같은 특정 도메인 데이터셋에 적
용해 보세요. 모든 기술적 개념이 자체 토큰을 갖게 되나요? 이러한 과정은 범용 언어 모델이 사
용자의 목적에 얼마나 적합한지 판단하는 데 유용한 단서를 제공합니다.
NOTE
_
토크나이저 훈련 세트의 모든 고유 개별 문자가 자체 토큰을 갖게 되므로 향후 추론 과정에서 만나는
모든 토큰이 훈련 세트에 있는 문자들로만 구성되는 한
OOV
토큰이 발생하지 않는 것이 보장됩니다. 그러나 유
니코드는
100
만 개 이상의 코드 포인트와 약
15
만 개의 유효한 문자로 구성되므로
3
만 개 크기의 어휘에 모두
담을 수 없습니다. 따라서 입력 텍스트에 훈련 세트에 없는 문자가 포함된다면 그 문자에
<UNK>
토큰이 할당된
다는 의미입니다.
이 문제를 해결하는 데 바이트 레벨
BPE
라고 하는
BPE
의 변형이 사용됩니다. 바이트 레벨
BPE ...
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.