Update handler.py

handler.py

@@ -41,9 +41,9 @@ class EndpointHandler:
 
         # pass inputs with all kwargs in data
         if parameters is not None:
-            outputs = self.model.generate(inputs, max_new_tokens=880, num_return_sequences=1, eos_token_id=self.tokenizer.eos_token_id, **parameters)
+            outputs = self.model.generate(inputs, num_return_sequences=1, eos_token_id=self.tokenizer.eos_token_id, **parameters) # removed max_new_tokens=880, will test and pass in max_new_tokens in config later
         else:
-            outputs = self.model.generate(inputs, max_new_tokens=880, num_return_sequences=1, eos_token_id=self.tokenizer.eos_token_id)
+            outputs = self.model.generate(inputs, num_return_sequences=1, eos_token_id=self.tokenizer.eos_token_id)
 
         # postprocess the prediction
         prediction = self.tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)