diff --git a/beginner_source/blitz/data_parallel_tutorial.py b/beginner_source/blitz/data_parallel_tutorial.py
index aca9b3ad12..2eb025ed49 100644
--- a/beginner_source/blitz/data_parallel_tutorial.py
+++ b/beginner_source/blitz/data_parallel_tutorial.py
@@ -9,7 +9,7 @@
 
 .. code:: python
 
-    device = torch.device("cuda:0")
+    device = torch.device("cuda")
     model.to(device)
 
 Then, you can copy all your tensors to the GPU: