Finetuning of gemma2 model using LORA

[Shiv-am-04]

Description of the feature request:

I have added a new notebook in the Gemma directory which is for finetuning gemma2 model using LORA which PEFT technique useful when finetuning in low resource environment.

What problem are you trying to solve with this feature?

This can solve the problem which is, we are unable to finetune the LLM models because of lack of computational resource. Hence, this helps everyone to understand how finetuning can be done in resource constraint environment

Any other information you'd like to share?

No response