Update handler for Colab-generated model

handler.py

@@ -14,7 +14,8 @@ class EndpointHandler():
     def __init__(self, path=""):
         # self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
         # self.tokenizer = AutoTokenizer.from_pretrained("optimum/sbert-all-MiniLM-L6-with-pooler")
-        self.onnx_extractor = pipeline("feature-extraction", model="optimum/sbert-all-MiniLM-L6-with-pooler", accelerator="ort")
+        model_regular = ORTModelForFeatureExtraction.from_pretrained("", file_name="model.onnx", from_transformers=False)
+        self.onnx_extractor = pipeline(task, model=model_regular, tokenizer=tokenizer)
         # self.model.to(self.device)
         # print("model will run on ", self.device)