[Doctest] Add configuration_vision_text_dual_encoder.py (#19580)

* initial commit

* few suggested changes

src/transformers/models/vision_text_dual_encoder/configuration_vision_text_dual_encoder.py

@@ -57,7 +57,7 @@ class VisionTextDualEncoderConfig(PretrainedConfig):
 
     >>> config = VisionTextDualEncoderConfig.from_vision_text_configs(config_vision, config_text, projection_dim=512)
 
-    >>> # Initializing a BERT and ViT model
+    >>> # Initializing a BERT and ViT model (with random weights)
     >>> model = VisionTextDualEncoderModel(config=config)
 
     >>> # Accessing the model configuration
@@ -65,7 +65,7 @@ class VisionTextDualEncoderConfig(PretrainedConfig):
     >>> config_text = model.config.text_config
 
     >>> # Saving the model, including its configuration
-    >>> model.save_pretrained("my-model")
+    >>> model.save_pretrained("vit-bert")
 
     >>> # loading model and config from pretrained folder
     >>> vision_text_config = VisionTextDualEncoderConfig.from_pretrained("vit-bert")

utils/documentation_tests.txt

@@ -118,6 +118,7 @@ src/transformers/models/van/modeling_van.py
 src/transformers/models/videomae/modeling_videomae.py
 src/transformers/models/vilt/modeling_vilt.py
 src/transformers/models/vision_encoder_decoder/modeling_vision_encoder_decoder.py
+src/transformers/models/vision_text_dual_encoder/configuration_vision_text_dual_encoder.py
 src/transformers/models/vit/configuration_vit.py
 src/transformers/models/vit/modeling_vit.py
 src/transformers/models/vit/modeling_tf_vit.py