Update handler file

handler.py

@@ -25,14 +25,14 @@ class EndpointHandler:
         inputs = f"[INST] {inputs} [/INST]"
 
         # preprocess
-        input_ids = self.tokenizer(inputs, return_tensors="pt").input_ids
-        input_ids = input_ids.to(self.model.device)
+        inputs = self.tokenizer(inputs, return_tensors="pt")
+        inputs = inputs.to(self.model.device)
 
         # pass inputs with all kwargs in data
         if parameters is not None:
-            outputs = self.model.generate(input_ids, **parameters)
+            outputs = self.model.generate(inputs, **parameters)
         else:
-            outputs = self.model.generate(input_ids)
+            outputs = self.model.generate(inputs)
 
         # postprocess the prediction
         prediction = self.tokenizer.decode(outputs[0], skip_special_tokens=True)