add feature: export (quantize) from Llama2.c format

[Hafez Mousavi]

Thanks a lot for your educational and informative project. I tried quantizing the already provided tinystories llama2.c format .bin files using the export.py, but as far as I understood it was not supported. On the export.py file llama.c is mentioned as supported input but apparently it is not. Is it possible to add this feature?
I am relatively new to all this so please don't mind if my point was incorrect. thanks again.