Update README.md

README.md

@@ -72,11 +72,13 @@ What sets bert-lite apart is its ability to learn from minimal data while delive
 
 ## 🔤 Quick Demo: Contextual Magic  
 Here’s bert-lite in action with a simple masked language task:  
+
 ```python
 from transformers import pipeline
 mlm = pipeline("fill-mask", model="boltuix/bert-lite")
 result = mlm("The cat [MASK] on the mat.")
 print(result[0]['sequence'])  # ✨ "The cat sat on the mat."
+
 ```
 ---
 
@@ -140,7 +142,6 @@ for sentence in masked_sentences:
 
 ## 🔤 Masked Language Model (MLM)'s Output
 ```python
-
 Input: The robot can [MASK] the room in minutes.
 ✨ → the robot can leave the room in minutes. (score: 0.1608)
 ✨ → the robot can enter the room in minutes. (score: 0.1067)