Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Adding ONNX Support to ALBERT Token and Sequence Classification and Question Answering annotators #13956

Conversation

danilojsl
Copy link
Contributor

Description

This PR adds ONNX Support for:

  • AlbertQuestionAnswering
  • AlbertSequenceClassification
  • AlbertTokenClassification

Motivation and Context

Adding ONNX support for faster inference

How Has This Been Tested?

Screenshots (if appropriate):

Types of changes

  • Bug fix (non-breaking change which fixes an issue)
  • Code improvements with no or little impact
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)

Checklist:

  • My code follows the code style of this project.
  • My change requires a change to the documentation.
  • I have updated the documentation accordingly.
  • I have read the CONTRIBUTING page.
  • I have added tests to cover my changes.
  • All new and existing tests passed.

SPARKNLP-892 Adding ONNX support for AlbertSequenceClassification
SPARKNLP-893 Adding ONNX support for AlbertTokenClassification
SPARKNLP-892 Adding ONNX support for AlbertSequenceClassification
SPARKNLP-893 Adding ONNX support for AlbertTokenClassification
@danilojsl danilojsl added new-feature Introducing a new feature DON'T MERGE Do not merge this PR labels Sep 4, 2023
@maziyarpanahi maziyarpanahi changed the title Adding ONNX Support for Albert Adding ONNX Support to ALBERT Token and Sequence Classification and Question Answering annotators Sep 7, 2023
@maziyarpanahi maziyarpanahi changed the base branch from master to release/511-release-candidate September 7, 2023 16:28
@maziyarpanahi maziyarpanahi merged commit fae2344 into release/511-release-candidate Sep 7, 2023
6 checks passed
maziyarpanahi added a commit that referenced this pull request Sep 11, 2023
…date

* [SPARKNLP-906] Fix reading suffix (#13945)

* Sparknlp 888 Add ONNX support to MPNet embeddings (#13955)

* adding onxx support to mpnet

* remove name in test

* updating default name for mpnet models in scala and python

* updating default model name

* Adding ONNX Support to ALBERT Token and Sequence Classification and Question Answering annotators (#13956)

* SPARKNLP-891 Adding ONNX support for AlbertQuestionAnswering
SPARKNLP-892 Adding ONNX support for AlbertSequenceClassification
SPARKNLP-893 Adding ONNX support for AlbertTokenClassification

* SPARKNLP-891 Adding ONNX support for AlbertQuestionAnswering
SPARKNLP-892 Adding ONNX support for AlbertSequenceClassification
SPARKNLP-893 Adding ONNX support for AlbertTokenClassification

* SPARKNLP-884 Enabling getVectors method to get word vectors as spark dataframe (#13957)

* [SPARKNLP-890] ONNX E5 MPnet example (#13958)

* Bump version to 5.1.1

* [SPARKNLP-891] [SPARKNLP-892] [SPARKNLP-893] Adding docs for ONNX support in AlbertXXX

* Fix misspelling [skip test]

* Fixing onnx saving path bug (#13959)

* fixing onnx write issue on windows

* fixing indentation

* fixing formatting

* fixing formatting

* final formatting fix

* Fix onnx saving bug

---------

Co-authored-by: Devin Ha <t.ha@tu-berlin.de>
Co-authored-by: Maziyar Panahi <maziyar.panahi@iscpif.fr>

---------

Co-authored-by: Devin Ha <33089471+DevinTDHa@users.noreply.github.com>
Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com>
Co-authored-by: Danilo Burbano <37355249+danilojsl@users.noreply.github.com>
Co-authored-by: Danilo Burbano <danilo@johnsnowlabs.com>
Co-authored-by: Devin Ha <t.ha@tu-berlin.de>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
DON'T MERGE Do not merge this PR new-feature Introducing a new feature
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants