A change in controlling AI response

UserWarning: You have modified the pretrained model configuration to contro
l generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use a generation configuration file (see https://huggingface.co/
This line appears as I run the program via pycharm. Originally when I started working on the code, I was getting very erratic responses so I wrote a code to refine the response as I am using two models coherently together both gpt2 and roberta. The first usages before moving from pygtk window was clear"ish" but when I moved over to Kivy for some reason the responses seem more older modeled and erratic…Not sure if anyone has came across this issue and can point me in the right direction.