atelier: one-of-one card — cut, silhouette, GitHub Python. YAML preserved.

README.md

@@ -45,6 +45,37 @@ Adapters are on this repo. Abstain is MEASURED 3/6, not a pass. Not publication-
 
 QLoRA adapter on disclosed [`Qwen/Qwen2.5-1.5B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) (runtime `unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit`). Proposal-only brain navigator / abstain retrain. Doctrine v11 LOCKED. Λ = Conjecture 1 (advisory, never a theorem).
 
+
+
+<!-- SZL-ATELIER-CUT:v1:START -->
+## The cut
+
+Leaders ship v1 and changelog the rest. We name the retraining of silence as its own model. Failure is an artifact, not a footnote.
+
+A public retrain whose only job is to improve one metric: honest abstain under adversarial handles.
+
+### Silhouette → leave → SZL
+
+| Leader | Take, then tweak |
+|---|---|
+| Anthropic | Red-team → constitution update. We red-team → adapter. |
+| NVIDIA | Recipe re-run with a new seed and a signed delta. |
+| Unsloth | Same FastLanguageModel loop, new curriculum, new receipt. |
+
+Nobody else ships this combination. That is the point of a one-of-one.
+
+## Intended use
+
+Continue the abstain-retrain loop. Fail closed until the receipt lands.
+
+## Limitations
+
+- research-only
+- No signed R2 eval receipt in this atelier.
+
+Canonical GitHub: [`szl-holdings/szl-forge`](https://github.com/szl-holdings/szl-forge/blob/main/khipu/)
+<!-- SZL-ATELIER-CUT:v1:END -->
+
 | | |
 |---|---|
 | **Artifact** | `adapter_model.safetensors` (147.8M) + `adapter_config.json` **AVAILABLE** |