Update handler.py

handler.py

@@ -37,9 +37,9 @@ class EndpointHandler:
 
         # pass inputs with all kwargs in data
         if parameters is not None:
-            outputs = self.model.generate(**inputs, **parameters)
+            outputs = self.model.generate(**inputs, max_new_tokens=880, **parameters)
         else:
-            outputs = self.model.generate(**inputs)
+            outputs = self.model.generate(**inputs, max_new_tokens=880)
 
         # postprocess the prediction
         prediction = self.tokenizer.decode(outputs[0], skip_special_tokens=True)