handler.py modification

handler.py

@@ -9,7 +9,7 @@ from io import BytesIO
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 class EndpointHandler:
-    def __init__(self, path: str = "morthens/qwen2-vl-inference"):
+    def __init__(self, path: str = "morthens/qwen2-vl-infer"):
         # Load the processor and model
         self.processor = AutoProcessor.from_pretrained(path)
         self.model = Qwen2VLForConditionalGeneration.from_pretrained(