Adds onnx ops to support debertav3/piiranha #3260
Open
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
Adds operations: - Add - Or - Tile - LessOrEqual - GreaterOrEqual Adds helpers `to_scalar_flexible` and `to_vec0_flexible` that both allow for more broad input definitions that fit what some onnx models export and are still scalar/vec0 but not "true" versions of them because the model didn't squeeze them.
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Outdated suggestions cannot be applied.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.
These are the changes I needed to run the ONNX version of Piiranha, which is debertaV3 based. I've since noticed that the debertaV2 model already in Candle also supports debertaV3, so I'm likely going to switch to using that, but thought the changes may be useful. Let me know if a subset is desired, I can cut it down to a smaller PR.
Adds operations:
Also adds and uses helpers
to_scalar_flexibleandto_vec0_flexiblethat both allow for more broad input definitions that fit what some onnx models export and are still scalar/vec0 but not "true" versions of them because the model didn't squeeze them.