reduce model size

app.py

@@ -34,7 +34,7 @@ print("loading the LLM......................................")
 # )
 
 llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GGUF", 
-                                           model_file="llama-2-7b-chat.Q3_K_L.gguf", 
+                                           model_file="llama-2-7b-chat.Q3_K_S.gguf", 
                                            model_type="llama", 
                                            temperature = 0.2,
                                            repetition_penalty = 1.5