Update README.md with new model card content

README.md

@@ -7,7 +7,7 @@ tags:
 - text-classification
 pipeline_tag: text-classification
 ---
-## Model Overview
+### Model Overview
 DistilBert is a set of language models published by HuggingFace. They are efficient, distilled version of BERT, and are intended for classification and embedding of text, not for text-generation. See the model card below for benchmarks, data sources, and intended use cases.
 
 Weights and Keras model code are released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE).
@@ -148,4 +148,4 @@ classifier = keras_hub.models.DistilBertClassifier.from_preset(
     preprocessor=None,
 )
 classifier.fit(x=features, y=labels, batch_size=2)
-```
+```