Card: plain attribution paragraph under the title

README.md

@@ -13,7 +13,7 @@ base_model:
 
 # muse-glimmer-30b
 
-> **Base model:** [meta-models/Muse-Glimmer-30B](https://huggingface.co/meta-models/Muse-Glimmer-30B). Weights revision [`f84ecc3a`](https://huggingface.co/meta-models/Muse-Glimmer-30B/tree/f84ecc3a0ea984a4c04542a84269e3d065350a6e). This package is derived from that model; its model card holds the licence, training and evaluation details.
+Derived from [meta-models/Muse-Glimmer-30B](https://huggingface.co/meta-models/Muse-Glimmer-30B). Weights revision [f84ecc3a](https://huggingface.co/meta-models/Muse-Glimmer-30B/tree/f84ecc3a0ea984a4c04542a84269e3d065350a6e). This represents the model implementation on Tenstorrent hardware. See the original model card for license, training, and evaluation details.
 
 Runs on **p300x2** (mesh `P300x2`) — 131,072-token context, up to 32 concurrent sequences.