Added handler

handler.py

@@ -0,0 +1,16 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from typing import Dict, List, Any
+
+class EndpointHandler():
+    def __init__(self, path=""):
+      self.model = AutoModelForCausalLM.from_pretrained(path, device_map="cuda", torch_dtype="auto", trust_remote_code=True)
+      self.tokenizer = AutoTokenizer.from_pretrained(path)
+      self.pipeline = pipeline("text-generation", model=self.model, tokenizer=self.tokenizer)
+
+    def __call__(self, data: Dict[str, Dict[str, Any]]) -> Any:
+        inputs = data["inputs"]["msg"]
+        parameters = data["args"]
+        prediction = self.pipeline(inputs, **parameters)
+        output = prediction[0]['generated_text']
+        return output