System Info

Windows 11 x86-64

Who can help?

No response

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction (minimal, reproducible, runnable)

conda create -n gemma-convert python=3.10
conda activate gemma-convert
pip install git+https://github.com/huggingface/accelerate.git
pip install git+https://github.com/huggingface/transformers.git
pip install git+https://github.com/huggingface/optimum.git
optimum-cli export onnx --model gemma-3-transformers-gemma-3-27b-it-v1 --task text-generation gemma-onnx/

result:

Loading checkpoint shards: 100%|███████████████████████████████████████████████████████| 12/12 [02:57<00:00, 14.79s/it]
Using a slow image processor as use_fast is unset and a slow processor was saved with this model. use_fast=True will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with use_fast=False.
Traceback (most recent call last):
File "C:\Users\codrut\miniconda3\envs\gemma-convert\lib\runpy.py", line 196, in _run_module_as_main
return run_code(code, main_globals, None,
File "C:\Users\codrut\miniconda3\envs\gemma-convert\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File "C:\Users\codrut\miniconda3\envs\gemma-convert\Scripts\optimum-cli.exe_main.py", line 7, in
File "C:\Users\codrut\miniconda3\envs\gemma-convert\lib\site-packages\optimum\commands\optimum_cli.py", line 208, in main
service.run()
File "C:\Users\codrut\miniconda3\envs\gemma-convert\lib\site-packages\optimum\commands\export\onnx.py", line 276, in run
main_export(
File "C:\Users\codrut\miniconda3\envs\gemma-convert\lib\site-packages\optimum\exporters\onnx_main.py", line 414, in main_export
onnx_export_from_model(
File "C:\Users\codrut\miniconda3\envs\gemma-convert\lib\site-packages\optimum\exporters\onnx\convert.py", line 1039, in onnx_export_from_model
raise ValueError(
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.

Expected behavior

Conversion to onnx is succesfull