Update app.py

app.py

@@ -10,10 +10,10 @@ from PIL import Image
 
 # Load Vision-Language Model
 vl_model = Qwen2VLForConditionalGeneration.from_pretrained(
-    "Qwen/Qwen2-VL-2B-Instruct",
-    torch_dtype=torch.bfloat16,
-    attn_implementation="flash_attention",
-    device_map="auto",
+    "Qwen/Qwen2-VL-2B-Instruct", torch_dtype="auto", device_map="auto"
+)
+Qwen2VLForConditionalGeneration.from_pretrained(
+    "Qwen/Qwen2-VL-2B-Instruct", torch_dtype="auto", device_map="auto"
 )
 vl_processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")