Update app.py

app.py

@@ -127,7 +127,7 @@ def initialize_llmchain(temperature, max_tokens, top_k, vector_db, progress=gr.P
     llm = HuggingFaceHub(repo_id=llm_model, model_kwargs={"temperature": temperature, 
                                                           "max_new_tokens": max_tokens, 
                                                           "top_k": top_k, 
-                                                          "load_in_8bit": False})
+                                                          "load_in_8bit": True})
     
     progress(0.75, desc="Defining buffer memory...")
     #memory = ConversationBufferMemory(memory_key="chat_history",output_key='answer',return_messages=True)