Add metadata for dataset used to train model

This is a small PR to add the dataset used to train your model to the YAML metadata section. This metadata makes the link between the model and the dataset easy to see on the Hugging Face Hub.

README.md

@@ -1,17 +1,19 @@
 ---
 tags:
 - generated_from_keras_callback
-- id 
+- id
 - Indonesian
 license: mit
 dataset:
 - id_puisi
 widget:
-- text : "SENJA"
-- text : "BERANI"
+- text: SENJA
+- text: BERANI
 model-index:
 - name: Sultannn/gpt2-ft-id-puisi
   results: []
+datasets:
+- Sultannn/id_recipe
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should