Can someone tell me how to benchmark LLama_v2_7b model on jetson Orin AGX with different quantization methods?

Can someone tell me how to benchmark LLama_v2_7b model on jetson Orin AGX with different quantization methods and also how to get perplexity score

Hi, thanks for reaching out. This is the forum for NVIDIA AI Workbench. You could try to find the right forum here.