logoalt Hacker News

monocasayesterday at 11:55 PM0 repliesview on HN

I mean, one if the big issues I've had is that it doesn't really store the compute graph. It only stores a string of the foundational architecture, along with parameter metadata to allow you to rebuild the compute graph.

That means that every foundational model architecture requires new code in whatever is consuming the gguf to support that model.