Minimize public model card details

README.md

@@ -1,61 +1,32 @@
 ---
 license: apache-2.0
-library_name: coreml
-pipeline_tag: text-generation
 inference: false
 tags:
-  - coreml
-  - apple-silicon
-  - macos
-  - neural-engine
-  - speculative-decoding
-  - dflash
   - doppel
+  - runtime-artifact
 ---
 
-# Doppel speculative-decoding companion
+# Doppel runtime artifact
 
-This repository is Doppel's distribution channel for an app-specific Core ML
-conversion of
-[`z-lab/Qwen3.5-9B-DFlash`](https://huggingface.co/z-lab/Qwen3.5-9B-DFlash).
-Doppel uses it as a Neural Engine draft companion while its target model
-performs verification.
+This repository contains a versioned runtime artifact consumed by compatible
+Doppel releases.
 
-## Intended use
+It is not a standalone model, SDK, or supported public API. Its format,
+compatibility contract, and behavior are private implementation details and
+may change without notice. No external loading, conversion, integration, or
+evaluation guidance is provided.
 
-These artifacts are intended to be downloaded, verified, and invoked by
-compatible Doppel releases on Apple-silicon Macs running macOS 15 or later.
-They are an optimization for Doppel's on-device inference path.
+The repository contains no customer data.
 
-This is not a standalone language model, text generator, or supported
-developer API. It omits a standalone vocabulary head and depends on Doppel's
-exact target model, hidden-state contract, cache lineage, verification logic,
-and runtime orchestration. Loading the Core ML packages individually does not
-constitute a valid or supported inference path. For research or general DFlash
-use, start with the upstream model and project.
+<details>
+<summary>License and attribution</summary>
 
-## Artifact and integrity notes
-
-The source checkpoint is split into app-specific Core ML packages. The
-repository's `manifest.json` is the authoritative compatibility and artifact
-inventory; it records the integrity hashes checked by Doppel. Core ML's local
-compilation cache is deliberately not distributed.
-
-The repository contains no user prompts, conversations, model caches,
-telemetry, or other customer data.
-
-## Limitations
-
-This companion is qualified only as part of Doppel's complete speculative
-decoder. It must not be evaluated as an independent generator, and compatibility
-must not be inferred from a shared tokenizer or architecture name.
-
-## License and attribution
-
-The DFlash checkpoint is provided under the
+This distribution includes modified material derived from
+[`z-lab/Qwen3.5-9B-DFlash`](https://huggingface.co/z-lab/Qwen3.5-9B-DFlash),
+provided under the
 [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0).
-Doppel pairs the conversion with the separately licensed
-[`Ornith-1.0-9B`](https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B)
-target. This converted distribution remains subject to the applicable
-upstream terms. Doppel provides no support or warranty for use outside the
-Doppel app.
+The source link is provided for attribution and does not define a supported
+Doppel compatibility contract. No warranty or support is provided for use
+outside Doppel.
+
+</details>