Hacker News Reader

Our skippy library is a patch queue on top of llama that allows us to access internal information, such as activations, and filter tensors on model load.

View on HN

This really should be in the blogpost. It’s both useful info and basic courtesy to be explicit about which underlying inferencing engine you are using

We didnt post it, we use a library (iroh) who featured us - so we are here answering any Q’s instead :)

Reply on news.ycombinator.com