Added example usage

docs/source/model_doc/xlnet.rst

@@ -39,14 +39,14 @@ XLNet
 ``XLNetForTokenClassification``
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: transformers.XLNetForTokenClassification`
+.. autoclass:: transformers.XLNetForTokenClassification
     :members:
 
 
 ``XLNetForMultipleChoice``
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: transformers.XLNetForMultipleChoice`
+.. autoclass:: transformers.XLNetForMultipleChoice
     :members:
 
 

src/transformers/configuration_bert.py

@@ -88,6 +88,23 @@ class BertConfig(PretrainedConfig):
                 The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
             layer_norm_eps (:obj:`float`, optional, defaults to 1e-12):
                 The epsilon used by the layer normalization layers.
+
+        Example::
+
+            from transformers import BertModel, BertConfig
+
+            # Initializing a BERT bert-base-uncased style configuration
+            configuration = BertConfig()
+
+            # Initializing a model from the bert-base-uncased style configuration
+            model = BertModel(configuration)
+
+            # Accessing the model configuration
+            configuration = model.config
+
+        Attributes:
+            pretrained_config_archive_map (Dict[str, str]):
+                A dictionary containing all the available pre-trained checkpoints.
     """
     pretrained_config_archive_map = BERT_PRETRAINED_CONFIG_ARCHIVE_MAP
 

src/transformers/configuration_camembert.py

@@ -41,5 +41,22 @@ class CamembertConfig(RobertaConfig):
 
         The :class:`~transformers.CamembertConfig` class directly inherits :class:`~transformers.BertConfig`.
         It reuses the same defaults. Please check the parent class for more information.
+
+        Example::
+
+            from transformers import CamembertModel, CamembertConfig
+
+            # Initializing a CamemBERT configuration
+            configuration = CamembertConfig()
+
+            # Initializing a model from the configuration
+            model = CamembertModel(configuration)
+
+            # Accessing the model configuration
+            configuration = model.config
+
+        Attributes:
+            pretrained_config_archive_map (Dict[str, str]):
+                A dictionary containing all the available pre-trained checkpoints.
     """
     pretrained_config_archive_map = CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP

src/transformers/configuration_ctrl.py

@@ -63,6 +63,23 @@ class CTRLConfig(PretrainedConfig):
                 The epsilon to use in the layer normalization layers
             initializer_range (:obj:`float`, optional, defaults to 0.02):
                 The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+
+        Example::
+
+            from transformers import CTRLModel, CTRLConfig
+
+            # Initializing a CTRL configuration
+            configuration = CTRLConfig()
+
+            # Initializing a model from the configuration
+            model = CTRLModel(configuration)
+
+            # Accessing the model configuration
+            configuration = model.config
+
+        Attributes:
+            pretrained_config_archive_map (Dict[str, str]):
+                A dictionary containing all the available pre-trained checkpoints.
     """
 
     pretrained_config_archive_map = CTRL_PRETRAINED_CONFIG_ARCHIVE_MAP

src/transformers/configuration_distilbert.py

@@ -74,6 +74,23 @@ class DistilBertConfig(PretrainedConfig):
             seq_classif_dropout (:obj:`float`, optional, defaults to 0.2):
                 The dropout probabilities used in the sequence classification model
                 :class:`~tranformers.DistilBertForSequenceClassification`.
+
+        Example::
+
+            from transformers import DistilBertModel, DistilBertConfig
+
+            # Initializing a DistilBERT configuration
+            configuration = DistilBertConfig()
+
+            # Initializing a model from the configuration
+            model = DistilBertModel(configuration)
+
+            # Accessing the model configuration
+            configuration = model.config
+
+        Attributes:
+            pretrained_config_archive_map (Dict[str, str]):
+                A dictionary containing all the available pre-trained checkpoints.
     """
     pretrained_config_archive_map = DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP
 

src/transformers/configuration_gpt2.py

@@ -94,6 +94,23 @@ class GPT2Config(PretrainedConfig):
                 Argument used when doing sequence summary. Used in for the multiple choice head in
                 :class:`~transformers.GPT2DoubleHeadsModel`.
                 Add a dropout before the projection and activation
+
+        Example::
+
+            from transformers import GPT2Model, GPT2Config
+
+            # Initializing a GPT2 configuration
+            configuration = GPT2Config()
+
+            # Initializing a model from the configuration
+            model = GPT2Model(configuration)
+
+            # Accessing the model configuration
+            configuration = model.config
+
+        Attributes:
+            pretrained_config_archive_map (Dict[str, str]):
+                A dictionary containing all the available pre-trained checkpoints.
     """
 
     pretrained_config_archive_map = GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP

src/transformers/configuration_openai.py

@@ -94,6 +94,23 @@ class OpenAIGPTConfig(PretrainedConfig):
                 Argument used when doing sequence summary. Used in for the multiple choice head in
                 :class:`~transformers.OpenAIGPTDoubleHeadsModel`.
                 Add a dropout before the projection and activation
+
+        Example::
+
+            from transformers import OpenAIGPTConfig, OpenAIGPTModel
+
+            # Initializing a GPT configuration
+            configuration = OpenAIGPTConfig()
+
+            # Initializing a model from the configuration
+            model = OpenAIGPTModel(configuration)
+
+            # Accessing the model configuration
+            configuration = model.config
+
+        Attributes:
+            pretrained_config_archive_map (Dict[str, str]):
+                A dictionary containing all the available pre-trained checkpoints.
     """
 
     pretrained_config_archive_map = OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP

src/transformers/configuration_transfo_xl.py

@@ -97,6 +97,23 @@ class TransfoXLConfig(PretrainedConfig):
                 Parameters initialized by N(0, init_std)
             layer_norm_epsilon (:obj:`float`, optional, defaults to 1e-5):
                 The epsilon to use in the layer normalization layers
+
+        Example::
+
+            from transformers import TransfoXLConfig, TransfoXLModel
+
+            # Initializing a Transformer XL configuration
+            configuration = TransfoXLConfig()
+
+            # Initializing a model from the configuration
+            model = TransfoXLModel(configuration)
+
+            # Accessing the model configuration
+            configuration = model.config
+
+        Attributes:
+            pretrained_config_archive_map (Dict[str, str]):
+                A dictionary containing all the available pre-trained checkpoints.
     """
 
     pretrained_config_archive_map = TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP

src/transformers/configuration_xlm.py

@@ -129,7 +129,7 @@ class XLMConfig(PretrainedConfig):
                 :class:`~transformers.XLMForSequenceClassification`.
                 Add a dropout before the projection and activation
             start_n_top (:obj:`int`, optional, defaults to 5):
-                Used in the SQuAD evaluation script for XLM and XLNetV.
+                Used in the SQuAD evaluation script for XLM and XLNet.
             end_n_top (:obj:`int`, optional, defaults to 5):
                 Used in the SQuAD evaluation script for XLM and XLNet.
             mask_token_id (:obj:`int`, optional, defaults to 0):
@@ -137,6 +137,23 @@ class XLMConfig(PretrainedConfig):
             lang_id (:obj:`int`, optional, defaults to 1):
                 The ID of the language used by the model. This parameter is used when generating
                 text in a given language.
+
+        Example::
+
+            from transformers import XLMConfig, XLMModel
+
+            # Initializing a XLM configuration
+            configuration = XLMConfig()
+
+            # Initializing a model from the configuration
+            model = XLMModel(configuration)
+
+            # Accessing the model configuration
+            configuration = model.config
+
+        Attributes:
+            pretrained_config_archive_map (Dict[str, str]):
+                A dictionary containing all the available pre-trained checkpoints.
     """
 
     pretrained_config_archive_map = XLM_PRETRAINED_CONFIG_ARCHIVE_MAP

src/transformers/configuration_xlnet.py

@@ -106,9 +106,26 @@ class XLNetConfig(PretrainedConfig):
                 :class:`~transformers.XLNetForSequenceClassification` and :class:`~transformers.XLNetForMultipleChoice`.
                 Add a dropout after the projection and activation
             start_n_top (:obj:`int`, optional, defaults to 5):
-                Used in the SQuAD evaluation script for XLM and XLNetV.
+                Used in the SQuAD evaluation script for XLM and XLNet.
             end_n_top (:obj:`int`, optional, defaults to 5):
                 Used in the SQuAD evaluation script for XLM and XLNet.
+
+        Example::
+
+            from transformers import XLNetConfig, XLNetModel
+
+            # Initializing a XLNet configuration
+            configuration = XLNetConfig()
+
+            # Initializing a model from the configuration
+            model = XLNetModel(configuration)
+
+            # Accessing the model configuration
+            configuration = model.config
+
+        Attributes:
+            pretrained_config_archive_map (Dict[str, str]):
+                A dictionary containing all the available pre-trained checkpoints.
     """
 
     pretrained_config_archive_map = XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP