LLM offsets logic consolidate w/ checks and test case fix #1422
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
|
This pull request was exported from Phabricator. Differential Revision: D65010820 |
Summary: Slight bug in the retry GitHub workflow causes failing workflows to rerun indefinitely. This _should_ fix it Differential Revision: D65008676
Summary: Add __call__ to TokenizerLike for transformers compatibility Differential Revision: D64998805
Summary: Use the __call__ method of tokenizers that returns a BatchEncoding with offsets. This allows us to grab text from the fully decoded string and not make assumptions about how many tokens correspond to a single string. Differential Revision: D64998804
Summary: visualize_image_attr_multiple can return a List[Axes], adds proper annotations to satisfy mypy Why casting is necessary: numpy/numpy#24738 https://github.com/matplotlib/matplotlib/blob/v3.9.2/lib/matplotlib/pyplot.py#L1583C41-L1584C1 Differential Revision: D64998799
Summary: Adds enough typing to get rid of `captum/metrics/_core/infidelity.py:498: note: By default the bodies of untyped functions are not checked, consider using --check-untyped-defs [annotation-unchecked]` Differential Revision: D64998800
Summary: Fix pyre/mypy errors in infidelity.py. Introduce new BaselineTupleType Differential Revision: D64998803
Summary: Fix incorrect **kwargs annotation Differential Revision: D65001879
Summary: Add base class BaseLLMAttribution to consolidate repeat logic between perturbation/gradient-based LLM attr classes Differential Revision: D65008854
Summary: Consolidate offsets logic with extra checks to one function. May be used to later group data in gradient LLM attribution. Test case fixed as a result of checks. Differential Revision: D65010820
craymichael
force-pushed
the
export-D65010820
branch
from
27be35c
to
e232eb1
Compare
|
This pull request was exported from Phabricator. Differential Revision: D65010820 |
|
This pull request has been merged in 492ae0e. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary: Consolidate offsets logic with extra checks to one function. May be used to later group data in gradient LLM attribution. Test case fixed as a result of checks.
Differential Revision: D65010820