Update app.py

app.py

@@ -34,6 +34,9 @@ def process(model_id, dataset):
 
     # Step 3: Text tokenization
 
+    def preprocess_function(examples):
+        return tokenizer(examples["text"], padding="max_length", truncation=True)
+    
     tokenizer = AutoTokenizer.from_pretrained("bert-base-cased")
 
     # Step 4: Apply tokenization to dataset