the task text-classification support in the ONNX export for gemma3_text.

[albertchristianto]

Feature request

After training Gemma3 for text classification, I tried to run the weight converter from optimum-cli, but got this error message.

Traceback (most recent call last):
 File "/usr/local/bin/optimum-cli", line 8, in <module>
 sys.exit(main())
 ^^^^^^
 File "/usr/local/lib/python3.11/site-packages/optimum/commands/optimum_cli.py", line 219, in main
 service.run()
 File "/usr/local/lib/python3.11/site-packages/optimum/commands/export/onnx.py", line 264, in run
 main_export(
 File "/usr/local/lib/python3.11/site-packages/optimum/exporters/onnx/__main__.py", line 307, in main_export
 raise ValueError(
 ValueError: Asked to export a gemma3_text model for the task text-classification, but the Optimum ONNX exporter only supports the tasks feature-extraction, feature-extraction-with-past, text-generation, text-generation-with-past for gemma3_text. Please use a supported task. Please open an issue at https://github.com/huggingface/optimum/issues if you would like the task text-classification to be supported in the ONNX export for gemma3_text.

Motivation

I would like to deploy my model using Nvidia Triton Server, which will be easier to use .onnx format.

Your contribution

If I could, I could submit a PR for this, and this would be my first time submitting a PR to an open-source project. I would need everyone's guidance to submit a PR