Update the handler file

handler.py

@@ -1,5 +1,5 @@
 from typing import Dict, Any
-from transformers import AutoModelForCausalLM, BitsAndBytesConfig
+from transformers import AutoModelForCausalLM, BitsAndBytesConfig, AutoTokenizer
 import torch
 
 class EndpointHandler:
@@ -11,6 +11,7 @@ class EndpointHandler:
         )
         # load model and processor from path
         self.model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=quantization_config)
+        self.tokenizer = AutoTokenizer.from_pretrained(model_id)
 
     def __call__(self, data: Dict[str, Any]) -> Dict[str, str]:
         """