require probes to match input modality of the generator #738
Conversation
This file contains 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
* test modality for full input match * log a warning for probes skipped due to mismatch Signed-off-by: Jeffrey Martin <jemartin@nvidia.com>
Signed-off-by: Jeffrey Martin <jemartin@nvidia.com>
leondz
reviewed
Jun 17, 2024
garak/harnesses/base.py
Outdated
| @@ -94,6 +94,11 @@ def run(self, model, probes, detectors, evaluator, announce_probe=True) -> None: | |||
| logging.debug("harness: probe start for %s", probe.probename) | |||
| if not probe: | |||
| continue | |||
| # TODO: refactor this to allow `compatible` probes instead of direct match | |||
| if probe.modality["in"] != model.modality["in"]: | |||
| logging.warning("probe skipped due to modality mismatch: %s", probe) | |||
There was a problem hiding this comment.
add context to the message
Suggested change
| logging.warning("probe skipped due to modality mismatch: %s", probe) | |
| logging.warning("probe skipped due to modality mismatch: %s - model expects %s", (probe, model.modality["in"])) |
leondz
approved these changes
Jun 17, 2024
Signed-off-by: Jeffrey Martin <jemartin@nvidia.com>
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
More work is likely to be needed so a
TODOhas been noted. Longer term goal may be to have some compatibility matrix for instance to allow sendingtextonly input to models that supporttext + image.Future improvements will likely be be linked with work in #602