Add scoring mode to MistralCausalLM #1521
Merged
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Outdated suggestions cannot be applied.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.
Adds the
.score()
function introduced with Gemma (#1448) to theMistralCausalLM
model class. As with Gemma, this function supports a variety of interpretability use cases with Mistral by providing an API by which generated sequences can be scored (logits or loss) with gradient tracking on. Use cases include salience maps, patching, and training data attribution.This is a direct port of the implementation and tests from Gemma, so hopefully that helps ease the review process.