Update handler.py

handler.py

@@ -10,9 +10,9 @@ device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 
 class EndpointHandler():
     def __init__(self, path=""):
-        self.processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+        self.processor = BlipProcessor.from_pretrained("zesquirrelnator/idefics2-8b-docvqa-finetuned-tutorial")
         self.model = BlipForConditionalGeneration.from_pretrained(
-            "Salesforce/blip-image-captioning-large"
+            "zesquirrelnator/idefics2-8b-docvqa-finetuned-tutorial"
         ).to(device)
         self.model.eval()
 
@@ -23,7 +23,7 @@ class EndpointHandler():
         if not encoded_images:
             return {"captions": [], "error": "No images provided"} 
 
-        texts = input_data.get("texts", ["a photography of"] * len(encoded_images)) 
+        texts = input_data.get("texts", ["move to red ball"] * len(encoded_images)) 
 
         try:
             raw_images = [Image.open(BytesIO(base64.b64decode(img))).convert("RGB") for img in encoded_images]