New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

최대 토큰 수 대응 #6

Open

1 task

FacerAin opened this issue Oct 15, 2023 · 0 comments

Assignees

Labels

Collaborator

FacerAin commented Oct 15, 2023 •

edited

Loading

🚀 Feature Request

현재는 러프하게 문자열 길이 1만까지로 LLM 입력 토큰 수 제한하고 있음.
하지만 한글 입력의 경우 1만 글자 이내가 4097 토큰을 넘어버릴 수 있음.
또한 llm이나 사용자 입장에서 바람직한 방법이 아님.
따라서 개선책 고민해보기.

TODO

gpt-3.5-turbo-16k 적용 -> cons: 요금 2배

📎 Additional context

https://platform.openai.com/tokenizer

FacerAin added the enhancement label

FacerAin self-assigned this

FacerAin added a commit that referenced this issue


          [#6] feat: change llm model to gpt-3.5-16k

a71fc50

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment