print(f"프롬프트: {prompt!r}, 생성된 텍스트: {generated_text!r}")
추측 디코딩은 §
8
.
3
“패턴
26
: 인퍼런스 최적화”에서도 논의한다.
8.1.3
예제
파이썬 코드 문서화 능력을 지닌
SLM
을 만든다고 하자.
이번 예제에서는 두 단계로 그런
SLM
을 만든다. 첫 단계에서는 문서화 능력이 있는
12B
모델
을
1B
매개변수 모델로 증류한다. 둘째 단계에서는 증류된 모델을
32
비트에서
4
비트로 양자
화한다. 이 예제의 전체 코드는 깃허브 저장소의
knowledge
_
distillation
.
py
파일에 있다.
증류
§
8
.
1
.
1
“문제” 절에서 보았듯이 젬마
3
1B
는 그 자체로는 문서화 작업을 잘 수행하지 못한다.
그때 사용한 프롬프트는 이런 모습이다.
다음 파이썬 코드를 상세하게 문서화하세요.
코드: ...
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.
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.
Head of Cybersecurity
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.
Field Engineer
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.
Data Platform Tech Lead
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.