Create handler.py

handler.py

@@ -0,0 +1,27 @@
+import torch
+from typing import Dict, List, Any
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+
+# get dtype
+dtype = torch.float16
+
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        # load the model
+        tokenizer = AutoTokenizer.from_pretrained(path)
+        model = AutoModelForCausalLM.from_pretrained(path, device_map="auto",torch_dtype=dtype)
+        # create inference pipeline
+        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None)
+
+        # pass inputs with all kwargs in data
+        if parameters is not None:
+            prediction = self.pipeline(inputs, **parameters)
+        else:
+            prediction = self.pipeline(inputs)
+        # postprocess the prediction
+        return prediction