Update app.py

app.py

@@ -35,7 +35,7 @@ def predict(message, history):
     history_transformer_format = history + [[message, ""]]
     stop = StopOnTokens()
 
-    messages = "".join(["".join(["\n<human>:"+item[0], "\n<bot>:"+item[1]])  #curr_system_message +
+    messages = "".join(["".join(["\n<USER>:"+item[0], "\n<ASSISTANT>:"+item[1]])  #curr_system_message +
                 for item in history_transformer_format])
 
     model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")