Update handler.py

handler.py

@@ -104,8 +104,8 @@ class EndpointHandler:
 
 
             gen_ids = self.model.generate(
-                attention_mask=attention_mask,
                 input_ids=input_ids,
+                attention_mask=attention_mask,
                 max_new_tokens=max_new_tokens,
                 do_sample=do_sample,
                 temperature=temperature if do_sample else None,