Updated the model card

README.md

@@ -15,8 +15,19 @@ widget:
 model-index:
 - name: DalaT5
   results:
-    - val_loss: 0.4126
-    - train_loss: 0.5390
+    - task:
+        name: Transliteration
+        type: text2text-generation
+      dataset:
+        name: Kazakh Cyrillic–Latin Transliteration Corpus
+        type: custom
+      metrics:
+        - name: Validation Loss
+          type: loss
+          value: 0.4126
+        - name: Training Loss
+          type: loss
+          value: 0.5390
 ---
 # DalaT5 — T5 Fine-Tuned on Cyrillic-to-Latin Kazakh 🇰🇿