merge peft model to base for deployment

[Nima-Nilchian]

Hi, I have fine-tuned a PEFT model using the NeMo Framework container, following the lora.ipynb notebook example. Now, I want to proceed with NeMo Framework inference container and deploy the fine-tuned model. How can I merge this PEFT model with the base model for deployment? generally how to deploy the PEFT fine-tuned model?