move to smaller model

handler.py

@@ -9,8 +9,8 @@ class EndpointHandler():
     def __init__(self, path=""):
         # Preload all the elements you are going to need at inference.
         self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-        self.model = SamModel.from_pretrained("facebook/sam-vit-huge").to(self.device)
-        self.processor = SamProcessor.from_pretrained("facebook/sam-vit-huge")
+        self.model = SamModel.from_pretrained("facebook/sam-vit-base").to(self.device)
+        self.processor = SamProcessor.from_pretrained("facebook/sam-vit-base")
 
     def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
         """

test_handler.py

@@ -2,7 +2,7 @@ import base64
 from handler import EndpointHandler
 
 my_handler = EndpointHandler(path=".")
-image = base64.b64encode(open("./car.png", "rb").read())
+image = base64.b64encode(open("../sam-vit-huge/car.png", "rb").read())
 
 input = {"image": image, "points": [[450, 600]]}
 result = my_handler(input)