We build on top of Mosaic or other open source libraries that people put together for training stuff and kind of adapted for yourself. Do things like TensorFlow and stuff work with these large language models or do you need other libraries? Yeah, so Tensor Flow and PyTorch are probably the two main machine learning libraries that people do deep learning systems on top of. GPT three and TPD four were probably trained on top of PyTorch. I think a lot of the stuff at Google like Palm and Bard and those sorts of things are trained on TensorFlow. They're actually very similar in this sort of converging to that kind of similar ideas too as well.