Update app.py

app.py

@@ -22,7 +22,7 @@ def load_models():
                          tokenizer_path=f'{weight_path}/tokenizer.model', 
                          max_seq_len=100, 
                          max_batch_size=32,
-                         device="cpu",
+                         device="cuda",
                          model_parallel_size=1)
     return model