Upload handler.py

handler.py

@@ -8,7 +8,7 @@ class EndpointHandler:
         tokenizer = AutoTokenizer.from_pretrained(path)
         model = AutoModelForCausalLM.from_pretrained(path, low_cpu_mem_usage=True)
         # create inference pipeline
-        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, device=device)
+        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
     def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
         inputs = data.pop("inputs", data)