-
Notifications
You must be signed in to change notification settings - Fork 31.2k
DistilBERT is ExecuTorch compatible #34475
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
Conversation
qubvel
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks, just a few nits!
Can you please also push empty commit[run_slow] distilbert to trigger slow test run, thanks!
ea7c7b0 to
b9afa5c
Compare
f8e80c2 to
5f3fbc3
Compare
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
qubvel
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks!
ArthurZucker
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM!@
* DistillBERT is ExecuTorch compatible * [run_slow] distilbert * [run_slow] distilbert --------- Co-authored-by: Guang Yang <[email protected]>
What does this PR do?
DistilBert is ExecuTorch compatible.
Unit Test:
RUN_SLOW=1 pytest tests/models/distilbert/test_modeling_distilbert.py -k test_export -vE2E test in ExecuTorch:
Patch pytorch/executorch#6509
python -m extension.export_util.export_hf_model -hfm="distilbert-base-uncased" -lm masked_lm./cmake-out/backends/xnnpack/xnn_executor_runner --model_path distilbert.pteBefore submitting
Pull Request section?
to it if that's the case. DistillBERT is ExecuTorch compatible #33835
Who can review?
@ArthurZucker
@qubvel