Added a conversion Python example for the Gemma 7B model.

[kuaashish]

Description

The Gemma 7B model conversion was missing, so updated the example for the newly supported model.

Fixes # (issue)

Checklist

Please ensure the following items are complete before submitting a pull request:

• My code follows the code style of the project.
• I have updated the documentation (if applicable).
• I have added tests to cover my changes.

Type of Change

Please check the relevant option below:

• Bug fix (non-breaking change which fixes an issue)
• Documentation update (non-breaking change which updates documentation)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)

Screenshots

Added the colab here https://colab.sandbox.google.com/drive/1nYJd20gxvQvgc8-PXQAn-Az9W4exSuxk?resourcekey=0-4e-P6wKuFz4ef8a50yubaQ

Additional Notes

Add any additional information or context about the pull request here.

[kuaashish]

Hi @schmidt-sebastian, @PaulTR

Could you please review the process for converting the Gemma 7B model using Colab? Additionally, made a few changes: the HF token field will now only appear when a Gemma model from Hugging Face is selected. Also, when the Gemma 7B model is available on GPU, the CPU option has been removed, as the 8-bit Gemma 7B model is compatible only with GPU.

Thank you!!

[schmidt-sebastian]

@woodyhoko should review this. Thanks for this contribution @kuaashish !