Update app.py

app.py

@@ -37,7 +37,9 @@ model_name = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 def tokenize_function(examples):
-    return tokenizer(examples["text"], truncation=True, padding="max_length", max_length=512)
+    tokens = tokenizer(examples["text"], truncation=True, padding="max_length", max_length=512)
+    tokens["labels"] = tokens["input_ids"].copy() # Use input as labels for unsupervised learning
+    return tokens
 
 tokenized_datasets = dataset.map(tokenize_function, batched=True)