Update README.md with new model card content

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: keras-hub
 ---
-### Model Overview
+## Model Overview
 A Keras model implementing the MixTransformer architecture to be used as a backbone for the SegFormer architecture. This model is supported in both KerasCV and KerasHub. KerasCV will no longer be actively developed, so please try to use KerasHub.
 
 References:
@@ -45,7 +45,7 @@ Here's the updated table with the input resolutions included in the descriptions
 | mit_b4_cityscapes_1024   | 60.85M     | MiT (MixTransformer) model with 41 transformer blocks, trained on the Cityscapes dataset with an input resolution of 1024x1024 pixels. |
 | mit_b5_cityscapes_1024   | 81.45M     | MiT (MixTransformer) model with 52 transformer blocks, trained on the Cityscapes dataset with an input resolution of 1024x1024 pixels. |
 
-### Example Usage
+## Example Usage
 Using the class with a `backbone`:
 
 ```