diff --git a/src/transformers/models/albert/modeling_albert.py b/src/transformers/models/albert/modeling_albert.py
index e8a69331e4..395081eded 100755
--- a/src/transformers/models/albert/modeling_albert.py
+++ b/src/transformers/models/albert/modeling_albert.py
@@ -693,12 +693,12 @@ class AlbertModel(AlbertPreTrainedModel):
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         if attention_mask is None:
diff --git a/src/transformers/models/bert/modeling_bert.py b/src/transformers/models/bert/modeling_bert.py
index 43af6741f8..f02d67a31a 100755
--- a/src/transformers/models/bert/modeling_bert.py
+++ b/src/transformers/models/bert/modeling_bert.py
@@ -936,13 +936,12 @@ class BertModel(BertPreTrainedModel):
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
-            batch_size, seq_length = input_shape
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         # past_key_values_length
diff --git a/src/transformers/models/bert_generation/modeling_bert_generation.py b/src/transformers/models/bert_generation/modeling_bert_generation.py
index 75ab959171..cbb8a7f12c 100755
--- a/src/transformers/models/bert_generation/modeling_bert_generation.py
+++ b/src/transformers/models/bert_generation/modeling_bert_generation.py
@@ -353,13 +353,12 @@ class BertGenerationEncoder(BertGenerationPreTrainedModel):
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
-            batch_size, seq_length = input_shape
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         # past_key_values_length
diff --git a/src/transformers/models/big_bird/modeling_big_bird.py b/src/transformers/models/big_bird/modeling_big_bird.py
index df69e43e8f..e7a15bec3b 100755
--- a/src/transformers/models/big_bird/modeling_big_bird.py
+++ b/src/transformers/models/big_bird/modeling_big_bird.py
@@ -2024,13 +2024,12 @@ class BigBirdModel(BigBirdPreTrainedModel):
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
-            batch_size, seq_length = input_shape
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         # past_key_values_length
diff --git a/src/transformers/models/canine/modeling_canine.py b/src/transformers/models/canine/modeling_canine.py
index dd273463de..18ca01031c 100644
--- a/src/transformers/models/canine/modeling_canine.py
+++ b/src/transformers/models/canine/modeling_canine.py
@@ -1119,13 +1119,12 @@ class CanineModel(CaninePreTrainedModel):
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
-            batch_size, seq_length = input_shape
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         if attention_mask is None:
diff --git a/src/transformers/models/ibert/modeling_ibert.py b/src/transformers/models/ibert/modeling_ibert.py
index 68f0521f99..61c775d9ff 100644
--- a/src/transformers/models/ibert/modeling_ibert.py
+++ b/src/transformers/models/ibert/modeling_ibert.py
@@ -803,13 +803,12 @@ class IBertModel(IBertPreTrainedModel):
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
-            batch_size, seq_length = input_shape
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         if attention_mask is None:
diff --git a/src/transformers/models/luke/modeling_luke.py b/src/transformers/models/luke/modeling_luke.py
index 4beb93cba0..b9004c1d49 100644
--- a/src/transformers/models/luke/modeling_luke.py
+++ b/src/transformers/models/luke/modeling_luke.py
@@ -887,13 +887,12 @@ class LukeModel(LukePreTrainedModel):
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
-            batch_size, seq_length = input_shape
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         if attention_mask is None:
diff --git a/src/transformers/models/megatron_bert/modeling_megatron_bert.py b/src/transformers/models/megatron_bert/modeling_megatron_bert.py
index 801af78897..3c49ea88b8 100755
--- a/src/transformers/models/megatron_bert/modeling_megatron_bert.py
+++ b/src/transformers/models/megatron_bert/modeling_megatron_bert.py
@@ -924,13 +924,12 @@ class MegatronBertModel(MegatronBertPreTrainedModel):
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
-            batch_size, seq_length = input_shape
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         # past_key_values_length
diff --git a/src/transformers/models/rembert/modeling_rembert.py b/src/transformers/models/rembert/modeling_rembert.py
index 3582df8a22..d8763a4138 100755
--- a/src/transformers/models/rembert/modeling_rembert.py
+++ b/src/transformers/models/rembert/modeling_rembert.py
@@ -829,13 +829,12 @@ class RemBertModel(RemBertPreTrainedModel):
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
-            batch_size, seq_length = input_shape
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         # past_key_values_length
diff --git a/src/transformers/models/roberta/modeling_roberta.py b/src/transformers/models/roberta/modeling_roberta.py
index 76a1a6c3d7..09472da767 100644
--- a/src/transformers/models/roberta/modeling_roberta.py
+++ b/src/transformers/models/roberta/modeling_roberta.py
@@ -789,13 +789,12 @@ class RobertaModel(RobertaPreTrainedModel):
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
-            batch_size, seq_length = input_shape
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         # past_key_values_length
diff --git a/src/transformers/models/roformer/modeling_roformer.py b/src/transformers/models/roformer/modeling_roformer.py
index 67c602f822..f08d3e5c8f 100644
--- a/src/transformers/models/roformer/modeling_roformer.py
+++ b/src/transformers/models/roformer/modeling_roformer.py
@@ -888,13 +888,12 @@ class RoFormerModel(RoFormerPreTrainedModel):
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
-            batch_size, seq_length = input_shape
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         # past_key_values_length
diff --git a/src/transformers/models/splinter/modeling_splinter.py b/src/transformers/models/splinter/modeling_splinter.py
index a6dd0984f4..1296db1250 100755
--- a/src/transformers/models/splinter/modeling_splinter.py
+++ b/src/transformers/models/splinter/modeling_splinter.py
@@ -683,13 +683,12 @@ class SplinterModel(SplinterPreTrainedModel):
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
-            batch_size, seq_length = input_shape
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         # past_key_values_length
diff --git a/src/transformers/models/visual_bert/modeling_visual_bert.py b/src/transformers/models/visual_bert/modeling_visual_bert.py
index c4cdda9e0d..21f5e01362 100755
--- a/src/transformers/models/visual_bert/modeling_visual_bert.py
+++ b/src/transformers/models/visual_bert/modeling_visual_bert.py
@@ -767,10 +767,8 @@ class VisualBertModel(VisualBertPreTrainedModel):
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
-            batch_size, seq_length = input_shape
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
@@ -779,6 +777,7 @@ class VisualBertModel(VisualBertPreTrainedModel):
                 f"`visual_embeds` can not be of type {type(visual_embeds)} when using a VisualBert Model."
             )
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         visual_input_shape = visual_embeds.size()[:-1]
diff --git a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_{{cookiecutter.lowercase_modelname}}.py b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_{{cookiecutter.lowercase_modelname}}.py
index d19d225c1c..f9596b1728 100755
--- a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_{{cookiecutter.lowercase_modelname}}.py
+++ b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_{{cookiecutter.lowercase_modelname}}.py
@@ -846,13 +846,12 @@ class {{cookiecutter.camelcase_modelname}}Model({{cookiecutter.camelcase_modelna
             raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
         elif input_ids is not None:
             input_shape = input_ids.size()
-            batch_size, seq_length = input_shape
         elif inputs_embeds is not None:
             input_shape = inputs_embeds.size()[:-1]
-            batch_size, seq_length = input_shape
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
+        batch_size, seq_length = input_shape
         device = input_ids.device if input_ids is not None else inputs_embeds.device
 
         # past_key_values_length