They do, and I was using the "new" models before the update. Perhaps there is tuning or bug fixes for them? Or they just want to confirm that these are supported. There are some new models that do have different architectures, so sometimes an update is necessary.
Phi 3 has a unique architecture that needed some additions to llama.cpp's conversion script. Also Phi 3 is an absolute mess, there's no reliable way to latch on to when it's done writing a message and no one wants to admit it, people are patching around it instead.
ex. I could condition on "\n\n<|assistant|>||<|system|>||<|user>", but it'd still be wrong.
Pretty much everything Phi 3 feels like it needed to all come out within 48 hours a month too early. The ONNX genai library doesn't work on Mac, at all, the mobile SDKs don't support it...sigh
