Implement

app.py

@@ -25,7 +25,7 @@ async def chat(history, limit: int = 1024, temp: float = 0.8, top_k: int = 40, t
     global ai
     if ai is None:
         model_id = "TheBloke/Llama-2-7B-Chat-GGML"
-        model_file = "llama-2-7b-chat.ggmlv3.q5_K_M.bin"
+        model_file = "llama-2-7b-chat.ggmlv3.q3_K_M.bin"
 
         engine = LlamaCTransformersEngine(model_id,
             model_file,