Update handler.py

Increasing response token limit

handler.py

@@ -23,7 +23,7 @@ class EndpointHandler:
 
         # pass inputs with all kwargs in data
         if parameters is not None:
-            prediction = self.pipeline(inputs, **parameters)
+            prediction = self.pipeline(inputs, max_new_tokens=2048, **parameters)
         else:
             prediction = self.pipeline(inputs)
         # postprocess the prediction