szl-khipu / hf /TinyKhipu-Nano /README.md
betterwithage's picture
szl-khipu 0.1.0 — kernels + tiny trained silhouettes
c38dddf verified
|
Raw
History Blame Contribute Delete
1.75 kB
metadata
license: apache-2.0
library_name: numpy
tags:
  - governed-ai
  - szl-holdings
  - doctrine-v11
  - nano
  - synthetic

TinyKhipu-Nano

Four features in. NAVIGATE or ABSTAIN out. Abstain is the default class, not a post-hoc filter.

Family. nano · Evidence. SYNTHETIC · Weights. numpy · Params. 4-6-2 · Not 1.5B.

Hub: SZLHOLDINGS/TinyKhipu-Nano

The cut

Leaders train models to answer. We train a silhouette to shut up when overlap is thin or the lure is adversarial. This nano is the 4-6-2 silhouette of that cut. Not 1.5B.

A navigator that has never seen document text — only handles — and still knows when to refuse the walk.

Silhouette → leave → SZL

Leader Take, then tweak
Anthropic Refusal as a typed output, not a polite paragraph.
NVIDIA Guardrail inside the head, not a sidecar.
Unsloth The 1.5B QLoRA is the grown form of this MLP.

Nobody else ships this combination. That is the point of a one-of-one.

Intended use

Unit-test the NAVIGATE|ABSTAIN schema before GPU spend.

Limitations

  • Synthetic features. Perfect holdout is a design fact, not a field claim.
  • The 1.5B abstain rate is 2/6 — this nano does not wash that.

Honesty

Claim Label
This card's numbers SYNTHETIC
Energy / joules UNAVAILABLE unless a signed meter says MEASURED
Λ uniqueness Conjecture 1 OPEN — not a theorem
GGUF as the signed object FALSE

Doctrine v11 LOCKED · 749 declarations · 14 axioms · 163 sorries · locked-proven 8.

Apache-2.0. Copyright 2026 SZL Holdings · Stephen P. Lutar Jr. · ORCID 0009-0001-0110-4173.