Added API to retrieve indices from the quantization layer #41
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
facebook-github-bot
added
the
CLA Signed
ankitade
reviewed
May 12, 2022
RdoubleA
force-pushed
the
rafiayub/get_quantised_vectors
branch
from
f5be9f9 to
c8eb2d9
Compare
langong347
approved these changes
May 17, 2022
|
@RdoubleA has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: Exposes the indices of the embedding vectors that were chosen in the quantisation layer during nearest neighbor lookup. These indices can be used in downstream tasks, such as a transformer decoder for cross-modal retrieval/generation. Pull Request resolved: #41 Test Plan: Expanded existing unit tests in `test/modules/layers/test_quantisation.py::TestQuantisation::test_quantised_output` and ran `pytest test/modules/layers/test_quantisation.py` Reviewed By: langong347 Differential Revision: D36462737 Pulled By: RdoubleA fbshipit-source-id: dc568e9402ef471afd99207d27c679caca8b8198
RdoubleA
force-pushed
the
rafiayub/get_quantised_vectors
branch
from
967754d to
abb1463
Compare
|
This pull request was exported from Phabricator. Differential Revision: D36462737 |
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Outdated suggestions cannot be applied.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:
Exposes the indices of the embedding vectors that were chosen in the quantisation layer during nearest neighbor lookup. These indices can be used in downstream tasks, such as a transformer decoder for cross-modal retrieval/generation.
Test plan:
Expanded existing unit tests in
test/modules/layers/test_quantisation.py::TestQuantisation::test_quantised_outputand ranpytest test/modules/layers/test_quantisation.py