Update README.md

README.md

@@ -16,4 +16,6 @@ The model is developed to process diverse inputs, including images and text, fac
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/kl5GWBP9WS0D4uwd1t3S7.png)
 
-This version of Cephalo, lamm-mit/Cephalo-LaTeX-Phi-3-vision-128k-4b-alpha, is trained to convert images of equations to LaTeX code. The model architecture is as follows:
+## Model Capabilities
+
+This version of Cephalo, lamm-mit/Cephalo-LaTeX-Phi-3-vision-128k-4b-alpha, is trained to convert images of equations to LaTeX code.