Update app.py

app.py

@@ -16,18 +16,18 @@ from ultralytics import YOLO
 import gradio as gr
 
 # # default: Load the model on the available device(s)
-model = Qwen2VLForConditionalGeneration.from_pretrained(
-    "Qwen/Qwen2-VL-7B-Instruct", torch_dtype="auto", device_map="auto"
-)
-
-# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
 # model = Qwen2VLForConditionalGeneration.from_pretrained(
-#     "Qwen/Qwen2-VL-7B-Instruct",
-#     torch_dtype=torch.bfloat16,
-#     attn_implementation="flash_attention_2",
-#     device_map="auto",
+#     "Qwen/Qwen2-VL-7B-Instruct", torch_dtype="auto", device_map="auto"
 # )
 
+# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
+model = Qwen2VLForConditionalGeneration.from_pretrained(
+    "Qwen/Qwen2-VL-7B-Instruct",
+    torch_dtype=torch.bfloat16,
+    attn_implementation="flash_attention_2",
+    device_map="auto",
+)
+
 # default processer
 processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")