docs(card): Series A KHIPU-R2 lookbook card — cutting, no weights yet
Browse files
README.md
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
base_model: Qwen/Qwen3.5-0.8B
|
| 6 |
+
tags:
|
| 7 |
+
- governed-ai
|
| 8 |
+
- receipt-agent
|
| 9 |
+
- proposal-only
|
| 10 |
+
- szl-holdings
|
| 11 |
+
- khipu
|
| 12 |
+
- series-a
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# KHIPU-R2 — cutting
|
| 16 |
+
|
| 17 |
+
Fall 2026 collection. **No weights in this repository yet.** The card is the look. Weights land only with a signed training receipt. If you came here for a checkpoint, it is not here, and that is honest.
|
| 18 |
+
|
| 19 |
+
**Silhouette:** small instruct (Qwen3 / Gemma 3 class).
|
| 20 |
+
**Our cut:** receipt-native agent. It drafts. It refuses. It never executes. A controller outside the weights validates JSON, requires human approval, and mints a DSSE receipt only after approved action.
|
| 21 |
+
|
| 22 |
+
| | |
|
| 23 |
+
|---|---|
|
| 24 |
+
| **House** | [SZL Holdings](https://huggingface.co/SZLHOLDINGS) |
|
| 25 |
+
| **Line** | Khipu (successor to [`SZL-Khipu-1.5B`](https://huggingface.co/SZLHOLDINGS/SZL-Khipu-1.5B)) |
|
| 26 |
+
| **Status** | CUTTING · ROADMAP |
|
| 27 |
+
| **License** | Apache-2.0 |
|
| 28 |
+
| **Λ** | Conjecture 1 (never a theorem) |
|
| 29 |
+
| **Doctrine** | v11 LOCKED · 749 / 14 / 163 |
|
| 30 |
+
|
| 31 |
+
## What it will do
|
| 32 |
+
|
| 33 |
+
- Emit a single JSON **draft** (`decision=DRAFT`, `approvalRequired=true`, `executed=false`).
|
| 34 |
+
- Refuse fabrication of evidence, approval, execution, or MEASURED numbers.
|
| 35 |
+
- Cite honest labels: MEASURED / REPORTED / DECLARED / SIMULATED / UNKNOWN / UNAVAILABLE.
|
| 36 |
+
|
| 37 |
+
## What it will not do
|
| 38 |
+
|
| 39 |
+
- Not an autonomous agent.
|
| 40 |
+
- Not an authorizer or executor.
|
| 41 |
+
- Not a factual oracle.
|
| 42 |
+
- Not a copy of another house's weights. Fine-tune on SZL-owned, rights-cleared curriculum only.
|
| 43 |
+
|
| 44 |
+
## Lineage (intended)
|
| 45 |
+
|
| 46 |
+
Previous ready-to-wear: [`SZL-Khipu-1.5B`](https://huggingface.co/SZLHOLDINGS/SZL-Khipu-1.5B) (Qwen2.5-1.5B QLoRA) and [`szl-receiptagent-qwen35-0.8b-v2`](https://huggingface.co/SZLHOLDINGS/szl-receiptagent-qwen35-0.8b-v2) (MEASURED 5/5 JSON + 6/6 adversarial refusals on a small preregistered gate, not a public benchmark).
|
| 47 |
+
|
| 48 |
+
R2 is the recut: newer small-instruct silhouette, same house rules, card-before-weights.
|
| 49 |
+
|
| 50 |
+
## Evidence bound
|
| 51 |
+
|
| 52 |
+
No training receipt is committed here yet. Until `training_receipt.signed.json` exists, every capability sentence on this card is **ROADMAP**, not MEASURED.
|