Skip to content

Adding Onnx Support For Megatron-Bert #2169

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.

Sign up for GitHub

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

Merged
echarlaix merged 4 commits into from
Jan 28, 2025
Merged

Adding Onnx Support For Megatron-Bert #2169

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0902505
Adding Onnx Support For Megatron-Bert
Jan 26, 2025
914d157
fix style
echarlaix Jan 27, 2025
1ea797d
fix style
echarlaix Jan 27, 2025
fdd97d4
fix style
echarlaix Jan 27, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions optimum/exporters/onnx/model_configs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,6 +171,10 @@ class RemBertOnnxConfig(BertOnnxConfig):
DEFAULT_ONNX_OPSET = 11


class MegatronBertOnnxConfig(BertOnnxConfig):
DEFAULT_ONNX_OPSET = 11


class DistilBertOnnxConfig(BertOnnxConfig):
DEFAULT_ONNX_OPSET = 14 # now uses F.scaled_dot_product_attention by default for transformers>=4.46.0

Expand Down
9 changes: 9 additions & 0 deletions optimum/exporters/tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -877,6 +877,15 @@ class TasksManager:
onnx="MobileBertOnnxConfig",
tflite="MobileBertTFLiteConfig",
),
"megatron-bert": supported_tasks_mapping(
"feature-extraction",
"fill-mask",
"text-classification",
"multiple-choice",
"token-classification",
"question-answering",
onnx="MegatronBertOnnxConfig",
),
"mobilevit": supported_tasks_mapping(
"feature-extraction",
"image-classification",
Expand Down
1 change: 1 addition & 0 deletions tests/exporters/exporters_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -197,6 +197,7 @@
"hf-internal-testing/tiny-random-UniSpeechSatForXVector": ["audio-xvector"],
},
"audio-spectrogram-transformer": "Ericwang/tiny-random-ast",
"megatron-bert": "hf-internal-testing/tiny-random-MegatronBertModel",
# Disabled for now because some operator seems to not be supported by ONNX.
# "mctct": "hf-internal-testing/tiny-random-MCTCTModel",
"speech-to-text": "hf-internal-testing/tiny-random-Speech2TextModel",
Expand Down