This repository has been archived by the owner on Nov 22, 2022. It is now read-only.
RoBERTa-QA JIT #1088
Closed
RoBERTa-QA JIT #1088
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
|
This pull request was exported from Phabricator. Differential Revision: D18218091 |
debowin
force-pushed
the
export-D18218091
branch
from
e3cb284 to
bfce4c1
Compare
debowin
pushed a commit
to debowin/pytext
that referenced
this pull request
Nov 5, 2019
Summary: Pull Request resolved: facebookresearch#1088 This diff torchscriptifies RoBERTa-QA to make it exportable in the same manner as BERT-QA. It also converts the has_answer_logits tensor to float before doing an argmax in squad_output_layer in order to use the FP16FairseqOptimizer. This otherwise breaks as argmax_cuda isn't supported for "Half" datatype. Differential Revision: D18218091 fbshipit-source-id: a53ea099da52e13784f327d533348524dfd6e5d5
|
This pull request was exported from Phabricator. Differential Revision: D18218091 |
debowin
pushed a commit
to debowin/pytext
that referenced
this pull request
Nov 5, 2019
Summary: Pull Request resolved: facebookresearch#1088 This diff torchscriptifies RoBERTa-QA to make it exportable in the same manner as BERT-QA. It also converts the has_answer_logits tensor to float before doing an argmax in squad_output_layer in order to use the FP16FairseqOptimizer. This otherwise breaks as argmax_cuda isn't supported for "Half" datatype. Differential Revision: D18218091 fbshipit-source-id: 96a112260a20ae836fbfad88994b6a934be2062c
debowin
force-pushed
the
export-D18218091
branch
from
bfce4c1 to
5b3d948
Compare
|
This pull request was exported from Phabricator. Differential Revision: D18218091 |
debowin
force-pushed
the
export-D18218091
branch
from
5b3d948 to
7dc5fcf
Compare
debowin
pushed a commit
to debowin/pytext
that referenced
this pull request
Nov 8, 2019
Summary: Pull Request resolved: facebookresearch#1088 This diff torchscriptifies RoBERTa-QA to make it exportable in the same manner as BERT-QA. It also converts the has_answer_logits tensor to float before doing an argmax in squad_output_layer in order to use the FP16FairseqOptimizer. This otherwise breaks as argmax_cuda isn't supported for "Half" datatype. Differential Revision: D18218091 fbshipit-source-id: d917a82663be0b42f337b84b048a18346ad39b41
|
This pull request was exported from Phabricator. Differential Revision: D18218091 |
Summary: Pull Request resolved: facebookresearch#1088 This diff torchscriptifies RoBERTa-QA to make it exportable in the same manner as BERT-QA. It also converts the has_answer_logits tensor to float before doing an argmax in squad_output_layer in order to use the FP16FairseqOptimizer. This otherwise breaks as argmax_cuda isn't supported for "Half" datatype. Reviewed By: hikushalhere Differential Revision: D18218091 fbshipit-source-id: 7c315b17fedfe82915d396179bef28367dce1d56
debowin
force-pushed
the
export-D18218091
branch
from
7dc5fcf to
2930f1f
Compare
|
This pull request was exported from Phabricator. Differential Revision: D18218091 |
|
This pull request has been merged in 8afd065. |
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:
This diff torchscriptifies RoBERTa-QA to make it exportable in the same manner as BERT-QA.
It also converts the has_answer_logits tensor to float before doing an argmax in squad_output_layer in order to use the FP16FairseqOptimizer. This otherwise breaks as argmax_cuda isn't supported for "Half" datatype.
Differential Revision: D18218091