How to Fine Tune Your Code LLMs to Your Code Base

The foundation model that you're referencing is not only a model used in Bard and Duet, but I believe through model garden and generative AI studio in Google Cloud, you're also able to build your own code LLMs on top of that same foundation model. There's an extra round of unsupervised training happening on palm to to teach palm to how to code. That's essentially coding. It's actually, it's a, see, I think the good analogy here is there is seg palm which is fine tune for security. Both, on version about code, as I was doing code completion, there's more than one thing, which is just going to be into the weeds