Exporting Gemma-3 models to ONNX is broken #45
Description
System Info
optimum v1.27.0, python 3.13, macosWho can help?
Information
- The official example scripts
- My own modified scripts
Tasks
- An officially supported task in the
examplesfolder (such as GLUE/SQuAD, ...) - My own task or dataset (give details below)
Reproduction (minimal, reproducible, runnable)
Running
uv run optimum-cli export onnx --model google/gemma-3-4b-it-qat-q4_0-unquantized --task text-generation gemma-3-4b/
Results in the following error:
Traceback (most recent call last):
File "/REDACTED_PATH_TO_PROJECT_DIR/.venv/bin/optimum-cli", line 10, in <module>
sys.exit(main())
~~~~^^
File "/REDACTED_PATH_TO_PROJECT_DIR/.venv/lib/python3.13/site-packages/optimum/commands/optimum_cli.py", line 208, in main
service.run()
~~~~~~~~~~~^^
File "/REDACTED_PATH_TO_PROJECT_DIR/.venv/lib/python3.13/site-packages/optimum/commands/export/onnx.py", line 276, in run
main_export(
~~~~~~~~~~~^
model_name_or_path=self.args.model,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
...<23 lines>...
**input_shapes,
^^^^^^^^^^^^^^^
)
^
File "/REDACTED_PATH_TO_PROJECT_DIR/.venv/lib/python3.13/site-packages/optimum/exporters/onnx/__main__.py", line 418, in main_export
onnx_export_from_model(
~~~~~~~~~~~~~~~~~~~~~~^
model=model,
^^^^^^^^^^^^
...<19 lines>...
**kwargs_shapes,
^^^^^^^^^^^^^^^^
)
^
File "/REDACTED_PATH_TO_PROJECT_DIR/.venv/lib/python3.13/site-packages/optimum/exporters/onnx/convert.py", line 1044, in onnx_export_from_model
raise ValueError(
f"Trying to export a {model_type} model, that is a custom or unsupported architecture, but no custom onnx configuration was passed as `custom_onnx_configs`. Please refer to https://huggingface.co/docs/optimum/main/en/exporters/onnx/usage_guides/export_a_model#custom-export-of-transformers-models for an example on how to export custom models. Please open an issue at https://github.com/huggingface/optimum/issues if you would like the model type {model_type} to be supported natively in the ONNX export."
)
ValueError: Trying to export a gemma3 model, that is a custom or unsupported architecture, but no custom onnx configuration was passed as `custom_onnx_configs`. Please refer to https://huggingface.co/docs/optimum/main/en/exporters/onnx/usage_guides/export_a_model#custom-export-of-transformers-models for an example on how to export custom models. Please open an issue at https://github.com/huggingface/optimum/issues if you would like the model type gemma3 to be supported natively in the ONNX export.
Given #67 has been reported&fixed, I infer that my problem above is a proper bug.
Expected behavior
optimum-cli can export gemma-3 models to onnx