🌐 [i18n-KO] Translated compressed_tensor.md to Korean#39517
Open
maximizemaxwell wants to merge 16 commits into
Open
🌐 [i18n-KO] Translated compressed_tensor.md to Korean#39517maximizemaxwell wants to merge 16 commits into
compressed_tensor.md to Korean#39517maximizemaxwell wants to merge 16 commits into
Conversation
Contributor
|
번역 고생하셨습니다. 번역하신 내용을 읽으면서 23,25,96라인에 씌여 있는 '활성화' 라는 표현이 적절하게 글의 원래 의도를 나타내고 있지 못한 것 같아서 이 부분을 어떻게 하면 더 적절하게 표현할 수 있을 지 고민해보면 좋을 것 같아요! 인터넷을 찾아봐도 적절한 표현이 없는 것 같아서 우선 고민해본 몇 가지 번역 제안을 드립니다. 활성화 양자화 -> 활성화 함수 기반 양자화 |
Contributor
Author
|
제안해주신 단어를 반영하였고, line 96의 문장은 전반적으로 구조를 약간 바꾸었습니다, |
Member
|
cc @stevhliu |
harheem
reviewed
Jul 21, 2025
harheem
left a comment
Contributor
There was a problem hiding this comment.
은수님 좋은 번역 정말 감사합니다
잘 읽히는 글이라 조금 욕심을 내서 수정 제안을 해보았습니다.
22~28 라인은 문장형인 것이 있고 단어로 끝나는 것이 있어서 단어로 끝나게 통일해보았습니다. 문장형으로 모두 통일하셔도 좋을 것 같아요! 편하게 의견주세요.
|
|
||
| [compressed-tensors](https://github.com/neuralmagic/compressed-tensors)는 [safetensors](https://github.com/huggingface/safetensors) 파일을 압축된 텐서 데이터 타입으로 확장해서, dense, int 양자화(int8), float 양자화(fp8), pack 양자화(int32로 패킹된 int4 또는 int8 가중치 양자화) 등 다양한 양자화·sparse 형식을 하나의 체크포인트 형식으로 저장하고 불러올 수 있게 합니다. | ||
|
|
||
| compressed-tensors는 [PEFT](https://huggingface.co/docs/peft)를 사용한 파인튜닝을 지원하며, 다음과 같은 기능들을 제공합니다. |
Contributor
There was a problem hiding this comment.
Suggested change
| compressed-tensors는 [PEFT](https://huggingface.co/docs/peft)를 사용한 파인튜닝을 지원하며, 다음과 같은 기능들을 제공합니다. | |
| compressed-tensors는 [PEFT](https://huggingface.co/docs/peft)를 사용한 미세 조정을 지원하며, 다음과 같은 기능들을 제공합니다. |
Contributor
There was a problem hiding this comment.
glossary에 따라 '미세 조정'으로 수정하였습니다
|
|
||
| compressed-tensors는 [PEFT](https://huggingface.co/docs/peft)를 사용한 파인튜닝을 지원하며, 다음과 같은 기능들을 제공합니다. | ||
|
|
||
| - fp8, int4, int8 가중치 및 활성화 함수 출력 정밀도. |
Contributor
There was a problem hiding this comment.
Suggested change
| - fp8, int4, int8 가중치 및 활성화 함수 출력 정밀도. | |
| - fp8, int4, int8 가중치 및 활성화 함수 출력 정밀도 |
stevhliu
approved these changes
Jul 21, 2025
stevhliu
left a comment
Member
There was a problem hiding this comment.
Thanks all, I'll merge once comments have been resolved! 🤗
Co-authored-by: Harheem Kim <[email protected]>
Co-authored-by: Harheem Kim <[email protected]>
Co-authored-by: Harheem Kim <[email protected]>
Co-authored-by: Harheem Kim <[email protected]>
jungnerd
reviewed
Jul 25, 2025
Co-authored-by: Woojun Jung <[email protected]>
Co-authored-by: Woojun Jung <[email protected]>
Co-authored-by: Woojun Jung <[email protected]>
Member
|
Thanks! Would you mind resolving the conflict before we merge please? 🤗 |
Contributor
|
@maximizemaxwell 충돌만 해결하면 머지될 것 같습니닷! 확인 부탁드립니다! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Translated the
compressed_tensor.mdfile of the documentation to Korean.Thank you in advance for your review.
Part of #20179
Before reviewing
[[lowercased-header]])Who can review? (Initial)
May you please review this PR?
@4N3MONE, @yijun-lee, @jungnerd , @harheem
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review? (Final)