Add pad token

Signed-off-by: Jael Gu <mengjia.gu@zilliz.com>

auto_transformers.py

@@ -96,6 +96,8 @@ class AutoTransformers(NNOperator):
                     raise e
             else:
                 self.tokenizer = tokenizer
+            if not self.tokenizer.pad_token:
+                self.tokenizer.pad_token = '[PAD]'
         else:
             log.warning('The operator is initialized without specified model.')
             pass
@@ -103,8 +105,9 @@ class AutoTransformers(NNOperator):
     def __call__(self, txt: str, return_sentence_emb: bool = False) -> numpy.ndarray:
         try:
             inputs = self.tokenizer(txt, padding=True, truncation=True, return_tensors="pt").to(self.device)
-        except Exception:
-            inputs = self.tokenizer(txt, truncation=True, return_tensors='pt').to(self.device)
+        except Exception as e:
+            log.error(f'Fail to tokenize inputs: {e}')
+            raise e
         try:
             outs = self.model(**inputs)
         except Exception as e:
@@ -143,10 +146,7 @@ class AutoTransformers(NNOperator):
                 raise AttributeError('Unsupported model_type.')
 
         dummy_input = '[CLS]'
-        try:
-            inputs = self.tokenizer(dummy_input, padding=True, truncation=True, return_tensors='pt')  # a dictionary
-        except Exception:
-            inputs = self.tokenizer(dummy_input, truncation=True, return_tensors='pt')
+        inputs = self.tokenizer(dummy_input, padding=True, truncation=True, return_tensors='pt')  # a dictionary
         if model_type == 'pytorch':
             torch.save(self._model, output_file)
         elif model_type == 'torchscript':