Update handler.py

handler.py

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