Mazin Karjikar
Quickstarting llama.cpp (#2)
6f00050 unverified
|
raw
history blame
259 Bytes

Local Models

This folder stores the local models being used by PerfGuru. In GitHub, this folder will be empty due to the size of models. Otherwise, when PerfGuru is ran on a machine, some local models such as Meta-Llama-3 should be used with llama.cpp.