Update app.py

app.py

@@ -53,7 +53,9 @@ def _launch_demo(args, model, tokenizer, config):
     def predict(_query, _chatbot, _task_history):
         print(f"User: {_parse_text(_query)}")
         _chatbot.append((_parse_text(_query), ""))
-        
+        input_ids = input_ids.to('cuda')
+        attention_mask = torch.ones(input_ids.shape).to('cuda')
+        pad_token_id = tokenizer.eos_token_id
         # Tokenize the input
         input_ids = tokenizer.encode(_query, return_tensors='pt')
         print("Input IDs:", input_ids)