Update app.py

app.py

@@ -32,7 +32,8 @@ def predict(message, history):
         temperature=0.1,
         repetition_penalty=2.0,
         length_penalty=-0.5,
-        num_beams=1
+        num_beams=1,
+        prompt_lookup_num_tokens=10
     )
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()  # Starting the generation in a separate thread.