Update app.py

app.py

@@ -55,7 +55,9 @@ if uploaded_file is not None:
 
         # Tokenize the dataset
         def tokenize_function(examples):
-            return tokenizer(examples["text"], padding="max_length", truncation=True, max_length=128)
+            tokens = tokenizer(examples["text"], padding="max_length", truncation=True, max_length=128)
+            tokens["labels"] = tokens["input_ids"].copy()  # Use input_ids as labels
+            return tokens
 
         tokenized_tweets = tweet_dataset.map(tokenize_function, batched=True)