Set missing seq_length variable when using inputs_embeds with ALBERT & Remove code duplication (#13152)

olenmg · web-flow · commit ef8d6f2b4a2c · 2021-08-31T06:51:25.000-04:00
* Set seq_length variable when using inputs_embeds

* remove code duplication
diff --git a/src/transformers/models/albert/modeling_albert.py b/src/transformers/models/albert/modeling_albert.py
@@ -693,12 +693,12 @@ def forward(
             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
@@ -936,13 +936,12 @@ def forward(
             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
@@ -353,13 +353,12 @@ def forward(
             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
@@ -2024,13 +2024,12 @@ def forward(
             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
@@ -1119,13 +1119,12 @@ def forward(
             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
@@ -803,13 +803,12 @@ def forward(
             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
@@ -887,13 +887,12 @@ def forward(
             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
@@ -924,13 +924,12 @@ def forward(
             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
@@ -829,13 +829,12 @@ def forward(
             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
@@ -789,13 +789,12 @@ def forward(
             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
@@ -888,13 +888,12 @@ def forward(
             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
@@ -683,13 +683,12 @@ def forward(
             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
@@ -767,10 +767,8 @@ def forward(
             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 @@ def forward(
                 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
@@ -846,13 +846,12 @@ def forward(
             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
