[docstring] Fix docstring for ErnieConfig, ErnieMConfig (#27029)

* Remove ErnieConfig, ErnieMConfig check_docstrings

* Run fix_and_overwrite for ErnieConfig, ErnieMConfig

* Replace <fill_type> and <fill_docstring> in configuration_ernie, configuration_ernie_m.py with type and docstring values

---------

Co-authored-by: vignesh-raghunathan <[email protected]>

src/transformers/models/ernie/configuration_ernie.py

@@ -81,14 +81,14 @@ class ErnieConfig(PretrainedConfig):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         layer_norm_eps (`float`, *optional*, defaults to 1e-12):
             The epsilon used by the layer normalization layers.
+        pad_token_id (`int`, *optional*, defaults to 0):
+            Padding token id.
         position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
             Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
             positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
             [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155).
             For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models
             with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
-        is_decoder (`bool`, *optional*, defaults to `False`):
-            Whether the model is used as a decoder or not. If `False`, the model is used as an encoder.
         use_cache (`bool`, *optional*, defaults to `True`):
             Whether or not the model should return the last key/values attentions (not used by all models). Only
             relevant if `config.is_decoder=True`.

src/transformers/models/ernie_m/configuration_ernie_m.py

@@ -61,19 +61,20 @@ class ErnieMConfig(PretrainedConfig):
             The dropout probability for all fully connected layers in the embeddings and encoder.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout probability used in `MultiHeadAttention` in all encoder layers to drop some attention target.
-        act_dropout (`float`, *optional*, defaults to 0.0):
-            This dropout probability is used in `ErnieMEncoderLayer` after activation.
-        max_position_embeddings (`int`, *optional*, defaults to 512):
+        max_position_embeddings (`int`, *optional*, defaults to 514):
             The maximum value of the dimensionality of position encoding, which dictates the maximum supported length
             of an input sequence.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the normal initializer for initializing all weight matrices. The index of padding
+            token in the token vocabulary.
+        pad_token_id (`int`, *optional*, defaults to 1):
+            Padding token id.
         layer_norm_eps (`float`, *optional*, defaults to 1e-05):
             The epsilon used by the layer normalization layers.
         classifier_dropout (`float`, *optional*):
             The dropout ratio for the classification head.
-        initializer_range (`float`, *optional*, defaults to 0.02):
-            The standard deviation of the normal initializer for initializing all weight matrices.
-        pad_token_id(`int`, *optional*, defaults to 1):
-            The index of padding token in the token vocabulary.
+        act_dropout (`float`, *optional*, defaults to 0.0):
+            This dropout probability is used in `ErnieMEncoderLayer` after activation.
 
     A normal_initializer initializes weight matrices as normal distributions. See
     `ErnieMPretrainedModel._init_weights()` for how weights are initialized in `ErnieMModel`.
@@ -97,7 +98,6 @@ def __init__(
         pad_token_id: int = 1,
         layer_norm_eps: float = 1e-05,
         classifier_dropout=None,
-        is_decoder=False,
         act_dropout=0.0,
         **kwargs,
     ):
@@ -114,5 +114,4 @@ def __init__(
         self.initializer_range = initializer_range
         self.layer_norm_eps = layer_norm_eps
         self.classifier_dropout = classifier_dropout
-        self.is_decoder = is_decoder
         self.act_dropout = act_dropout

utils/check_docstrings.py

@@ -166,8 +166,6 @@
     "ElectraTokenizerFast",
     "EncoderDecoderModel",
     "EncoderRepetitionPenaltyLogitsProcessor",
-    "ErnieConfig",
-    "ErnieMConfig",
     "ErnieMModel",
     "ErnieModel",
     "ErnieMTokenizer",