Skip to content

[i18n-ko] Translated fine_tuning_vlm_dpo_smolvlm_instruct.ipynb to Korean #296

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.

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

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

jungnerd
Copy link

@jungnerd jungnerd commented May 13, 2025

What does this PR do?

Translate fine_tuning_vlm_dpo_smolvlm_instruct.ipynb to Korean

Who can review?

@merveenoyan, may you please review this PR?

Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

@merveenoyan
Copy link
Collaborator

Hello, we need a Korean speaker to review this 🤗 thanks for the PR!

@mreraser
Copy link

Hello! @merveenoyan I think I can review this!

Copy link

@mreraser mreraser left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hello @jungnerd! I think you did a great job👍 — the translation feels really natural! I just have a few suggestions below.

  • (수정 전) 이 파인튜닝의 목표는 모델이 일관되게 선택된 답변을 선호하도록 해 환각 현상을 줄이는 것입니다.
  • (수정 후) 이 파인튜닝의 목표는 모델이 일관되게 선택된 답변을 선호하도록 해 환각(hallucination) 현상을 줄이는 것입니다.
  • (수정 전) # 처음으로 디코딩된 출력 텍스트를 반환합니다
  • (수정 후) # 첫번째로 디코딩된 출력 텍스트를 반환합니다
  • (수정 전) 사전학습(pre-trained) 모델만을 사용하는 Space도 아래 링크에서 확인할 수 있습니다:
  • (수정 후) 사전학습(pre-trained) 된 모델만을 사용하는 Space도 아래 링크에서 확인할 수 있습니다:

@jungnerd
Copy link
Author

Thank you, @mreraser ! 👍
I made some changes to the translations, and the translation looks fine now.
Would you mind reviewing this PR one more time? @merveenoyan

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants