I am new to working with LLMs. I have a finetuned LLAMA2 model in safe tensor format saved to my local disk. I want to load my model locally by running a python notebook. I have tried googling, and I find many examples on loading Stable diffusion models but noting much on loading LLAMA models.
Originally asked by Tej Kiran Boppana on Stack Exchange (stackoverflow) (CC BY-SA 4.0).
