This repository has been archived by the owner on Nov 22, 2022. It is now read-only.
support torchscriptify XLM-R #1138
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
facebook-github-bot
added
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D18487692 |
chenyangyu1988
added a commit
to chenyangyu1988/pytext
that referenced
this pull request
Nov 13, 2019
Summary: Pull Request resolved: facebookresearch#1138 The core part of this diff is to determine use ScriptTextModule or ScriptTokenModule in RoBERTa.torchscriptify(). Given concrete example: GPT2BPE need use ScriptTextModule and SentencePiece need to use ScriptTokenModule This diff have few changes 1) Introduce ScriptInputType to determine to use ScriptTextModule or ScriptTokenModule 2) ScriptTokenizer have API: input_type() to determine which ScriptInputType to support 3) Add torchscriptify() API for SentencePieceTokenizer Differential Revision: D18487692 fbshipit-source-id: 087ac278522273c4f9ba2bc3f99d57bc65fe0b16
chenyangyu1988
force-pushed
the
export-D18487692
branch
from
97facb8
to
c2801ef
Compare
|
This pull request was exported from Phabricator. Differential Revision: D18487692 |
Summary: Pull Request resolved: facebookresearch#1138 The core part of this diff is to determine use ScriptTextModule or ScriptTokenModule in RoBERTa.torchscriptify(). Given concrete example: GPT2BPE need use ScriptTextModule and SentencePiece need to use ScriptTokenModule This diff have few changes 1) Introduce ScriptInputType to determine to use ScriptTextModule or ScriptTokenModule 2) ScriptTokenizer have API: input_type() to determine which ScriptInputType to support 3) Add torchscriptify() API for SentencePieceTokenizer Differential Revision: D18487692 fbshipit-source-id: eb41a77ecb2b67f8473659859892f7ef5d323cad
chenyangyu1988
force-pushed
the
export-D18487692
branch
from
c2801ef
to
b7909dd
Compare
|
This pull request was exported from Phabricator. Differential Revision: D18487692 |
|
This pull request has been merged in bc000a6. |
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 core part of this diff is to determine use ScriptTextModule or ScriptTokenModule in RoBERTa.torchscriptify().
Given concrete example: GPT2BPE need use ScriptTextModule and SentencePiece need to use ScriptTokenModule
This diff have few changes
Differential Revision: D18487692