April 2026
Intermediate
592 pages
13h 28m
Korean
Content preview from 에이전트 시대의 AI 시스템 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.
143
2
장
콘텐츠 스타일의 제어
training_args = DPOConfig(output_dir="Qwen-DPO")
trainer = DPOTrainer(model=model, args=training_args,
processing_class=tokenizer, train_dataset=train_dataset)
trainer.train()
훈련이 완료되면 모델을 저장한다.
trainer.save_model(training_args.output_dir)
훈련된 모델을 배포할 수도 있고, 로컬 저장소에서 트랜스포머 파이프라인으로 불러와 기존 모
델 대신 사용할 수도 있다. 이 모델은 선택된 응답과 기각된 응답 집합에서 학습한 스타일로 결
과물을 생성할 것이다.
2.5.3
예제
LLM
을 이용해 중고 거래 광고를 생성하되, 지연시간 문제로 더 작은 모델을 사용하고 싶다고
가정해 보자. 여기서는 매개변수
0
.
5B
(
5
억)개 규모의 큐원
2
모델 (
Qwen2
-
0
.
5B
)을 사용한
다(전체 코드는 원서 깃허브 저장소의
examples
/
05
_
content
_
optimization
에 있다 ).
제로샷 학습은 효과가 없다
비교를 위해 제로샷 학습은 어떤지 시험해 보자. 다음은 모델에게 중고 거래 광고 문구의 생성
을 요청하는 프롬프트이다.
당신은 동네 온라인 그룹에 중고 물품을 판매하기 위해 ...
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.