Laya, fine-tuned on 99 privacy-scrubbed Rule #3 scenarios

Clean revision of laya-typed-decisions: trained from the base convaiinnovations/laya checkpoint on 99 hand-labeled, privacy-scrubbed Mind Project surfacing scenarios (surface_now vs hold_silent), superseding the revision trained on pre-scrub data. Held-out accuracy: 0.850 | Brier: 0.1066 (20 stratified held-out scenarios).

import laya
f"agent = laya.load("philipsubhan/laya-typed-decisions")
"

Downloads last month: -; Downloads are not tracked for this model. How to track

Safetensors

Model size

0.4B params

Tensor type

F16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support