해서는 모델의 생성 루프를 명시적으로 제어해야 한다. 방법은 어렵지 않다. 먼저, 미리 정해진
수(이 예제에서는
16
개)의 토큰을 생성하도록
pipe
.
model
.
generate
()
메서드를 호출한다.
results = pipe.model.generate(
**input_ids,
max_new_tokens=16,
num_beams=10,
output_scores=True,
)
이런 식으로
generate
()
를 처음 호출할 때
input
_
ids
는 사용자의 프롬프트를 토큰화해서
얻은 토큰
ID
들이다. 둘째 호출부터는 그때까지 생성된 시퀀스를
input
_
ids
에 덧붙여야 한
다. 이를테면 다음과 같은 식이다.
input_ids = pipe.tokenizer(
input_prompt +'\n'.join(text_so_far),
return_tensors="pt").to("cuda")
이 코드는 이전에 생성된 텍스트를 원래 프롬프트에 추가한 후 토큰화해서 토큰 ...
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.