Skip to content
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.

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

Support Gemma3 models #1197

Open
LarryatIntel opened this issue Mar 13, 2025 · 0 comments
Open

Support Gemma3 models #1197

LarryatIntel opened this issue Mar 13, 2025 · 0 comments
Assignees

Comments

@LarryatIntel
Copy link

Looks like Gemma3 models used new transformer, and optimum-cli has not supported it now, when can optimum-cli can support Gemma3?

(ov_llm) C:\Users\Local_Admin\models\Qwentest>optimum-cli export openvino -m google/gemma-3-1b-it --weight-format int4 --sym --group-size 128 --ratio 1.0 google/gemma-3-1b-it
:207: DeprecationWarning: The openvino.runtime module is deprecated and will be removed in the 2026.0 release. Please replace openvino.runtime with openvino.
Traceback (most recent call last):
File "", line 198, in run_module_as_main
File "", line 88, in run_code
File "C:\ProgramData\miniforge3\envs\ov_llm\Scripts\optimum-cli.exe_main
.py", line 7, in
File "C:\ProgramData\miniforge3\envs\ov_llm\Lib\site-packages\optimum\commands\optimum_cli.py", line 208, in main
service.run()
File "C:\ProgramData\miniforge3\envs\ov_llm\Lib\site-packages\optimum\commands\export\openvino.py", line 466, in run
main_export(
File "C:\ProgramData\miniforge3\envs\ov_llm\Lib\site-packages\optimum\exporters\openvino_main
.py", line 267, in main_export
raise ValueError(
ValueError: Trying to export a gemma3-text model, that is a custom or unsupported architecture, but no custom export configuration was passed as custom_export_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-intel/issues if you would like the model type gemma3-text to be supported natively in the OpenVINO export.

@eaidova eaidova self-assigned this Mar 13, 2025
@eaidova eaidova mentioned this issue Mar 13, 2025
3 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants