laya-english-coreml
A Core ML build of laya, for running typed decisions on on-device Apple runtimes instead of a hosted API.
Community card
What this is
A repackaged build of laya, not a separate model. The weights are the same; what changes is the runtime you can put them in and the hardware that will hold them.
How to run it
Core ML
Core ML runs on the Neural Engine, so the decision happens on the device with nothing leaving it. Full Core ML guide.
# Download the .mlpackage from the repository, then load it with coremltoolsA public number is a shortlist, not a decision
The only benchmark that settles which model you ship is one built from your own historical decisions. We freeze that test set, run the candidates against it, and hand back the threshold your error budget supports.