Repository navigation
Conversation
…d outputs requirement_check() and check_certainty() score from answer-token probabilities, so temperature rescales the score without adding randomness. Document this in the docstrings and the adapter guide. Refs generative-computing#1687 Assisted-by: IBM Bob Signed-off-by: pavani42 <sindiripavani01@gmail.com>
github-actions
Bot
added
the
documentation
This branch has not been deployed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pull Request
Issue
Fixes #1687
Description
Document how temperature and sampling options effect likelihood-based scores returned by adapter functions when using
LocalHFBackend.model_optionsdescription in thecheck_certainty()andrequirement_check()docstrings.guide (
docs/docs/advanced/intrinsics.md), covering temperature anddo_sample.This covers the documentation part of #1687. Returning the sampled label or
answer-token distribution (the issue's second suggestion) is not included and
would need a separate API change.
Testing
Attribution