Update app.py

app.py

@@ -14,4 +14,6 @@ from transformers import AutoTokenizer
 tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
 
 def preprocess_function(examples):
-    return tokenizer(examples["text"], truncation=True)
+    return tokenizer(examples["text"], truncation=True)
+    
+tokenized_imdb = imdb.map(preprocess_function, batched=True)