Update app.py

app.py

@@ -11,4 +11,7 @@ from datasets import load_dataset
 imdb = load_dataset("imdb")
 
 from transformers import AutoTokenizer
-tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
+tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
+
+def preprocess_function(examples):
+    return tokenizer(examples["text"], truncation=True)