Add anatomical attention GIF to model card

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/AnatomicalAttention.gif filter=lfs diff=lfs merge=lfs -text

README.md

@@ -20,9 +20,11 @@ metrics:
 
 **Layer-Wise Anatomical Attention model**
 
-[ArXiv Paper](https://arxiv.org/abs/2512.16841) | [LinkedIn](https://www.linkedin.com/in/devmuniz) | [GitHub Profile](https://github.com/devMuniz02) | [Portfolio](https://devmuniz02.github.io/) | [GitHub Repository](https://github.com/devMuniz02/layer-wise-anatomical-attention) | [Hugging Face Profile](https://huggingface.co/manu02)
-
-## What This Model Does
+[ArXiv Paper](https://arxiv.org/abs/2512.16841) | [LinkedIn](https://www.linkedin.com/in/devmuniz) | [GitHub Profile](https://github.com/devMuniz02) | [Portfolio](https://devmuniz02.github.io/) | [GitHub Repository](https://github.com/devMuniz02/layer-wise-anatomical-attention) | [Hugging Face Profile](https://huggingface.co/manu02)
+
+![Layer-Wise Anatomical Attention](assets/AnatomicalAttention.gif)
+
+## What This Model Does
 
 LAnA generates radiology reports from chest X-ray images. This training run uses resized chest X-ray PNG images from the CheXpert training split for optimization, while the repository also includes MIMIC-CXR support for test-time evaluation. The model expects a chest X-ray image as input and produces a free-text radiology report as output.