Update handler.py

handler.py

@@ -9,17 +9,17 @@ class EndpointHandler():
         device = "cuda:0" if torch.cuda.is_available() else "cpu"
         torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
-        model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-large", torch_dtype=torch_dtype, trust_remote_code=True).to(device)
-        processor = AutoProcessor.from_pretrained("microsoft/Florence-2-large", trust_remote_code=True)
+        self.model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-large", torch_dtype=torch_dtype, trust_remote_code=True).to(device)
+        self.processor = AutoProcessor.from_pretrained("microsoft/Florence-2-large", trust_remote_code=True)
 
 
     def predict_image(self, url, prompt):
         url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
         image = Image.open(requests.get(url, stream=True).raw)
 
-        inputs = processor(text=prompt, images=image, return_tensors="pt").to(device, torch_dtype)
+        inputs = self.processor(text=prompt, images=image, return_tensors="pt").to(device, torch_dtype)
 
-        generated_ids = model.generate(
+        generated_ids = self.model.generate(
             input_ids=inputs["input_ids"],
             pixel_values=inputs["pixel_values"],
             max_new_tokens=4096,