Upload 2 files

handler.py

@@ -0,0 +1,31 @@
+from typing import  Dict, List, Any
+from optimum.onnxruntime import ORTModelForSequenceClassification
+from transformers import AutoTokenizer
+from optimum.pipelines import pipeline
+
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        # load the optimized model
+        model = ORTModelForSequenceClassification.from_pretrained(path)
+        tokenizer = AutoTokenizer.from_pretrained(path)
+        # create inference pipeline
+        self.pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer, device=0)
+
+
+    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
+        """
+        Args:
+            data (:obj:):
+                includes the input data and the parameters for the inference.
+        Return:
+            A :obj:`list`:. The object returned should be a list of one list like [[{"label": 0.9939950108528137}]] containing :
+                - "label": A string representing what the label/class is. There can be multiple labels.
+                - "score": A score between 0 and 1 describing how confident the model is for this label/class.
+        """
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", dict())
+
+        prediction = self.pipeline(inputs, **parameters)
+
+        return prediction

requirements.txt

@@ -0,0 +1,2 @@
+transformers==4.44.2
+optimum[onnxruntime-gpu]==1.22.0