small changes

app.py

@@ -32,7 +32,9 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
         tokenize=True,
         add_generation_prompt=True,
         return_tensors="pt",
-    ).to("cuda" if torch.cuda.is_available() else "cpu")
+    )
+    inputs = inputs.to("cuda" if torch.cuda.is_available() else "cpu")
+    attention_mask = inputs.ne(tokenizer.pad_token_id).long()
     
     output = model.generate(
         input_ids=inputs,
@@ -54,6 +56,7 @@ demo = gr.ChatInterface(
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
+    type="messages"
 )
 
 if __name__ == "__main__":