Issue Report: Unable to Export Gemma 7b Model to ONNX Format in Optimum

[Harini-Vemula-2382]

System Info

Optimum Version: 1.18.0
Python Version: 3.8
Platform: Windows, x86_64

Who can help?

@michaelbenayoun @JingyaHuang @echarlaix
I am writing to report an issue I encountered while attempting to export a Gemma 7b model to ONNX format using Optimum.

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)

optimum-cli export onnx --model google/gemma-7b gemma7b_optimum_onnx/ --trust-remote-code

Expected behavior

I would expect Optimum to successfully export the Gemma 7b model to ONNX format without encountering any errors or issues.

[fxmarty]

Hi @Harini-Vemula-2382, thank you for the report. I can not reproduce the issue with torch==2.2.2, onnx==1.16.0, onnxruntime==1.17.3 on Optimum main (installed from source).

I'll do a release 1.19 today, let me know if this helps.

[Harini-Vemula-2382]

Still I am facing the same issue, tried multiple times!
Could you please help me in how to convert gemma into onnx format?