Update handler.py

handler.py

@@ -12,7 +12,7 @@ class EndpointHandler:
         tokenizer = AutoTokenizer.from_pretrained(path)
         model = AutoModelForCausalLM.from_pretrained(path, device_map="auto",torch_dtype=dtype)
         # create inference pipeline
-        self.pipeline = pipeline("conversational", model=model, tokenizer=tokenizer)
+        self.pipeline = pipeline('text-generation', model=model, tokenizer=tokenizer)
 
     def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
         inputs = data.pop("inputs", data)