Gemma Onnx suuport

[Kaya-P]

System Info

My system currently is 
python = 3.8 
optimum-intel : optimum-1.18.0.dev0

Who can help?

@JingyaHuang @echarlaix

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)

I am following the provided examples on #1714 but am running into some issues.
when I run
optimum-cli export onnx -m google/gemma-2b gemma_onnx

I get the following error

When I execute the python script provided I get the following error

Expected behavior

The expected behavior is for the model to compile and be stored in onnx form

[fxmarty]

Answered on the other thread

[tchen48]

@fxmarty can you give me your version of optimum and transformers? I am running in the latest version and still have the error:

ValueError: Trying to export a gemma 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 gemma to be supported natively in the ONNX export.

I am using the same command that you are using

[andyyeh75]

@fxmarty I encountered the same issue with this project as well while adding 'google/gemma-2b-it' as a LLM option.
openvino-llm-chatbot-rag

cc @tchen48

[IlyasMoutawwakil]

you'll need to install from main pip install optimum@git+https://github.com/huggingface/optimum.git for gemma support

[fxmarty]

Closing as supported on main. Please install from source till the next release.