Replace <fill_type> and <fill_docstring> in configuration_ernie, conf…

…iguration_ernie_m.py with type and docstring values
huggingface · Jan 9, 2024 · 63f6bfd · 63f6bfd
1 parent e0c767d
commit 63f6bfd
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 7 deletions.
diff --git a/src/transformers/models/ernie/configuration_ernie.py b/src/transformers/models/ernie/configuration_ernie.py
@@ -81,7 +81,8 @@ 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 (`<fill_type>`, *optional*, defaults to 0): <fill_docstring>
+        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

diff --git a/src/transformers/models/ernie_m/configuration_ernie_m.py b/src/transformers/models/ernie_m/configuration_ernie_m.py
@@ -65,14 +65,14 @@ class ErnieMConfig(PretrainedConfig):
             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): <fill_docstring>
+            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.
-        is_decoder (`<fill_type>`, *optional*, defaults to `False`): <fill_docstring>
         act_dropout (`float`, *optional*, defaults to 0.0):
             This dropout probability is used in `ErnieMEncoderLayer` after activation.
 
@@ -98,7 +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,
     ):
@@ -115,5 +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