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
Add RankGPT support inside RankLLM #12475
Conversation
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Any reason to remove (or move?) this notebook? (now it won't show up in the docs, maybe we should replace it with the one you added below?)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
oh i see, i'll add it back
from rank_llm.result import Result | ||
|
||
self._result = Result | ||
|
||
if model_enum == ModelType.VICUNA: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Curious why we removed the enum? Seemed helpful for validation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
we'd need to add another parameter gpt-type
, or continuously update the enums to match the available openai models.
I wanted to keep the API clean. Tho thinking more, i think its ok adding another optional parameter, if that sounds good.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
A couple of nits, but looks good otherwise
@logan-markewich fixed, lmk if looks good! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we also bump the version (patch) number in pyproject.toml?
Description