Trained Models & Weights
Collection
Published model weights, quantizations, recipes, and their training/inference labs. Published means the repository exists; signed receipts and model-c β’ 11 items β’ Updated β’ 1
Moons-Nano
Two interlocking moons. A 2-8-2 tanh MLP. The toy that teaches fail-closed before anyone touches 1.5B.
Family. nano Β· Evidence. MEASURED Β· Weights. numpy Β· Params. 2-8-2
The cut
Accuracy is the wrong headline. We publish holdout accuracy AND silhouette AND the decision boundary you can click. Leaders hide the toy. We hang it in the foyer.
A model card that is a laboratory: click the plane, watch the gate, read the loss.
Silhouette β leave β SZL
| Leader | Take, then tweak |
|---|---|
| Anthropic | Small, inspectable, no capability theater. |
| NVIDIA | MLP instead of cuDNN flex β the kernel idea at 2D. |
| Unsloth | SGD on 400 points, not QLoRA. Same honesty about scale. |
Nobody else ships this combination. That is the point of a one-of-one.
Intended use
Onboard the cut: measured numbers, visible boundary.
Limitations
- Toy. 2D. Noise 0.13. Not a product model.
Honesty
| Claim | Label |
|---|---|
| This card's numbers | MEASURED |
| Energy / joules | UNAVAILABLE unless a signed meter says MEASURED |
| Ξ uniqueness | Conjecture 1 OPEN β not a theorem |
| GGUF as the signed object | FALSE |
Doctrine v11 LOCKED Β· 749 declarations Β· 14 axioms Β· 163 sorries Β· locked-proven 8.
Apache-2.0. Copyright 2026 SZL Holdings Β· Stephen P. Lutar Jr. Β· ORCID 0009-0001-0110-4173.
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support