This repository has been archived by the owner on Nov 22, 2022. It is now read-only.
support XLM-R model Embedding in TorchScript #1278
Closed
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
Summary: The main purpose of the diff is to create a TorchScript model for XLM-R model with embedding as output How to TorchScriptify model with embedding? XLM-R model ---- PyText: torchscript_export_with_embedder ---> ScriptPyTextEmbeddingModule (texts: Optional[List[str]]) ---- Fluent2 wrapper: DocumentEmbedder (texts: texts: Optional[List[Optional[str]]], e.g SingleTextFeature) Details: 1. Create a general Script Embedding Module in PyText (e.g ScriptPyTextEmbeddingModule) ==> pytext/torchscript/module.py 2. Generalize the fluent2 Script Embedding Wrapper in fluent2 (e.g DocumentEmbedder), support both text and token feature ==> fblearner/flow/projects/fluent2/definition/transformers/contrib/pytext/torchscript.py 3. Combine xlm and xlm embedder (PyText one), implement embedding torchscriptify ==> pytext/pytext_embedder_helper.py 4. PyTextDocumentClassifierWithEmbedding support text_feature Reviewed By: kartikayk Differential Revision: D20320641 fbshipit-source-id: 90c33f75b098836534ee0587fa052ba7b922cb7b
facebook-github-bot
added
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D20320641 |
|
This pull request has been merged in 495e455. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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:
The main purpose of the diff is to create a TorchScript model for XLM-R model with embedding as output
How to TorchScriptify model with embedding?
XLM-R model
---- PyText: torchscript_export_with_embedder ---> ScriptPyTextEmbeddingModule (texts: Optional[List[str]])
---- Fluent2 wrapper: DocumentEmbedder (texts: texts: Optional[List[Optional[str]]], e.g SingleTextFeature)
Details:
==> fblearner/flow/projects/fluent2/definition/transformers/contrib/pytext/torchscript.py
Reviewed By: kartikayk
Differential Revision: D20320641