Launching today
ej
An 11MB local model for typed decisions in one pass
9 followers
An 11MB local model for typed decisions in one pass
9 followers
I built ej for a narrower problem than general classification: given some state and a set of decision questions whose options can be defined at runtime, return a probability distribution for each question in one pass. It handles choice, yes/no, and ordered scores, runs on CPU, needs no token generation, and ships as one 11.4 MB model file. The repo includes training, evaluation, adaptation, packed weights, and the benchmark harness.
