phanerozoic's picture
Add pruned model README
f929418 verified

Pruned Variant

Minimal subnetwork extracted from the full model via neuron ablation analysis.

Architecture

Layer Full Pruned
Hidden 1 32 11
Hidden 2 16 3
Parameters 833 139

Pruning Method

Systematic single-neuron ablation identified which neurons are critical (their removal degrades accuracy) versus redundant (their removal has no effect). Only 11 of 32 Layer-1 neurons and 3 of 16 Layer-2 neurons were critical. The minimal subnetwork retains only these neurons.

Verification

Correctness is proven in Coq for all 256 inputs, identical to the full network. See PrunedThresholdLogic.v in the GitHub repository.

Usage

from model import PrunedThresholdNetwork

model = PrunedThresholdNetwork.from_safetensors('model.safetensors')