Update app.py

app.py

@@ -59,7 +59,7 @@ def display_chat_history(chain):
 def create_conversational_chain(vector_store):
     load_dotenv()
     # Create llm
-    llm = CTransformers(model="NousResearch/Llama-2-7b-hf",
+    llm = CTransformers(model="NousResearch/Yarn-Llama-2-13b-128k",
                         streaming=True, 
                         callbacks=[StreamingStdOutCallbackHandler()],
                         model_type="llama", config={'max_new_tokens': 500, 'temperature': 0.01})