Add self-describing model card (mtp-sidecar)

README.md

@@ -0,0 +1,39 @@
+---
+base_model: Qwen/Qwen3.5-9B-Base
+tags:
+- mtp-sidecar
+- skulk
+- foxlight
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3.5-9B-Base/blob/main/LICENSE
+foxlight:
+  artifact_type: mtp-sidecar
+  source_repo: Qwen/Qwen3.5-9B-Base
+  source_revision: 68c46c4b3498877f3ef123c856ecfde50c39f404
+  target_model: Qwen/Qwen3.5-9B-Base
+  extracted_with: skulk-weights-publisher 0.1.0
+  generated_at: '2026-06-02T16:51:57Z'
+---
+
+# FoxlightAI/qwen3-5-9b-base-mtp
+
+This repository contains an **MTP speculative-decoding sidecar** derived from [`Qwen/Qwen3.5-9B-Base`](https://huggingface.co/Qwen/Qwen3.5-9B-Base). It is **not a standalone model** — it provides the multi-token-prediction heads used by [Skulk](https://github.com/Foxlight-Foundation/Skulk) to speculatively decode for the target model **`Qwen/Qwen3.5-9B-Base`**. The heads ship at full precision (**bf16, unquantized**) — they are the speculative drafter, where precision drives draft acceptance — so there is **one sidecar per base model** and it serves **every quantization** of the target.
+
+## Provenance
+
+| Field | Value |
+| --- | --- |
+| Artifact type | mtp-sidecar |
+| Source model | `Qwen/Qwen3.5-9B-Base` |
+| Source revision | `68c46c4b3498877f3ef123c856ecfde50c39f404` |
+| Target model | `Qwen/Qwen3.5-9B-Base` |
+| Extracted with | skulk-weights-publisher `0.1.0` |
+| Generated | 2026-06-02T16:51:57Z |
+
+## Usage
+
+Skulk loads this sidecar (`mtp.safetensors`) alongside the target model to enable MTP speculative decoding. It is referenced from the Skulk Weights Publisher catalog and fetched automatically by the Skulk shard downloader; it is not intended to be loaded standalone.
+
+## License
+
+This artifact is derived from [`Qwen/Qwen3.5-9B-Base`](https://huggingface.co/Qwen/Qwen3.5-9B-Base) and is published under that model's original license (**apache-2.0**), preserved unchanged. Refer to the source model's card for the full terms.