Update app.py

app.py

@@ -13,26 +13,27 @@ model = AutoModelForCausalLM.from_pretrained(model_id_or_path, device_map="auto"
 
 processor = AutoProcessor.from_pretrained(model_id_or_path, trust_remote_code=True)
 
-image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
-
-image = Image.open(requests.get(image_path, stream=True).raw)
-
-messages = [
-    {
-        "role": "user",
-        "content": [
-            {"text": None, "type": "image"},
-            {"text": "what is the image?", "type": "text"},
-        ],
-    }
-]
-
-text = processor.apply_chat_template(messages, add_generation_prompt=True)
-inputs = processor(text=text, images=image, return_tensors="pt")
-inputs["pixel_values"] = inputs["pixel_values"].to(model.dtype)
-inputs = {k: v.to(model.device) for k, v in inputs.items()}
 @spaces.GPU
 def run():
+        
+    image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
+    
+    image = Image.open(requests.get(image_path, stream=True).raw)
+    
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"text": None, "type": "image"},
+                {"text": "what is the image?", "type": "text"},
+            ],
+        }
+    ]
+    
+    text = processor.apply_chat_template(messages, add_generation_prompt=True)
+    inputs = processor(text=text, images=image, return_tensors="pt")
+    inputs["pixel_values"] = inputs["pixel_values"].to(model.dtype)
+    inputs = {k: v.to(model.device) for k, v in inputs.items()}
     with torch.inference_mode(), torch.cuda.amp.autocast(dtype=torch.bfloat16):
         output = model.generate(
             **inputs,