diff --git a/README.md b/README.md
index 0f3f461..063af4f 100644
--- a/README.md
+++ b/README.md
@@ -81,7 +81,7 @@ in [eval_configs/minigpt4_eval.yaml](eval_configs/minigpt4_eval.yaml#L10) at Lin
 Try out our demo [demo.py](demo.py) on your local machine by running
 
 ```
-python demo.py --cfg-path eval_configs/minigpt4_eval.yaml
+python demo.py --cfg-path eval_configs/minigpt4_eval.yaml  --gpu-id 0
 ```
 
 Here, we load Vicuna as 8 bit by default to save some GPU memory usage. 
diff --git a/demo.py b/demo.py
index 9e222d4..b3659f1 100644
--- a/demo.py
+++ b/demo.py
@@ -23,7 +23,7 @@ from minigpt4.tasks import *
 def parse_args():
     parser = argparse.ArgumentParser(description="Demo")
     parser.add_argument("--cfg-path", required=True, help="path to configuration file.")
-    parser.add_argument("--gpu_id", type=int, default=0, help="specify the gpu to load the model.")
+    parser.add_argument("--gpu-id", type=int, default=0, help="specify the gpu to load the model.")
     parser.add_argument(
         "--options",
         nargs="+",