add logprobs support for exl3 #373
Merged
Conversation
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
Signed-off-by: kingbri <[email protected]>
Member
|
Fancy seeing you here! Looks good, merged. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
Is your pull request related to a problem? Please describe.
exl3 backend code is missing logprobs support
Why should this feature be added?
logprobs are very useful both for roleplay plebs for easy rerolling from the middle of the message (as well as for generally getting some very convenient info about what the model could have said instead), as well as for programmers using using models for classification (asking to reply with a single token and looking at probabilities).
Examples
Additional context
The code is mostly copied from exl2 implementation. Works on my windows machine in a fresh installation; exl3 library does support logprobs via the same
return_top_tokensarg.