Onnx fix test #10663
Merged
Onnx fix test #10663
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
sgugger
approved these changes
Mar 11, 2021
| @@ -38,19 +38,23 @@ def forward(self, input_ids, some_other_args, token_type_ids, attention_mask): | |||
|
|
|||
|
|
|||
| class OnnxExportTestCase(unittest.TestCase): | |||
| MODEL_TO_TEST = ["bert-base-cased", "gpt2", "roberta-base"] | |||
There was a problem hiding this comment.
Removing roberta-base is on purpose here?
There was a problem hiding this comment.
Yeah, speeding up things a bit, Roberta and Bert share the exact same graph, so basically it's testing the same things twice.
LysandreJik
approved these changes
Mar 11, 2021
|
Merging now to rebase the slow tests and re-run them. |
Iwontbecreative
pushed a commit
to Iwontbecreative/transformers
that referenced
this pull request
Jul 15, 2021
* Allow to pass kwargs to model's from_pretrained when using pipeline. * Disable the use of past_keys_values for GPT2 when exporting to ONNX. * style * Remove comment. * Appease the documentation gods * Fix style Co-authored-by: Lysandre <lysandre.debut@reseau.eseo.fr>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
GPT2
past_keys_valuesformat seems to have changed since last time I checked, now exporting for each layer tuple with 2 elements.PyTorch's ONNX exporter doesn't seem to handle this format, so it was crashing with an error.
The PR assumes we don't currently support exporting
past_keys_valuesfor GPT2 and then disable the return of such values when constructing the model.In order to support this behavior,
pipeline()now ha amodel_kwargs: Dict[str, Any]parameter which forwards the dict of parameters to model'sfrom_pretrained(..., **model_kwargs).