added doc for openai GPT

pytorch_transformers/modeling_bert.py

@@ -154,6 +154,7 @@ class BertConfig(PretrainedConfig):
         :class:`~pytorch_transformers.BertConfig` is the configuration class to store the configuration of a
         `BertModel`.
 
+
         Arguments:
             vocab_size_or_config_json_file: Vocabulary size of `inputs_ids` in `BertModel`.
             hidden_size: Size of the encoder layers and the pooler layer.
@@ -193,31 +194,6 @@ class BertConfig(PretrainedConfig):
                  initializer_range=0.02,
                  layer_norm_eps=1e-12,
                  **kwargs):
-        """Constructs BertConfig.
-
-        Arguments:
-            vocab_size_or_config_json_file: Vocabulary size of `inputs_ids` in `BertModel`.
-            hidden_size: Size of the encoder layers and the pooler layer.
-            num_hidden_layers: Number of hidden layers in the Transformer encoder.
-            num_attention_heads: Number of attention heads for each attention layer in
-                the Transformer encoder.
-            intermediate_size: The size of the "intermediate" (i.e., feed-forward)
-                layer in the Transformer encoder.
-            hidden_act: The non-linear activation function (function or string) in the
-                encoder and pooler. If string, "gelu", "relu" and "swish" are supported.
-            hidden_dropout_prob: The dropout probabilitiy for all fully connected
-                layers in the embeddings, encoder, and pooler.
-            attention_probs_dropout_prob: The dropout ratio for the attention
-                probabilities.
-            max_position_embeddings: The maximum sequence length that this model might
-                ever be used with. Typically set this to something large just in case
-                (e.g., 512 or 1024 or 2048).
-            type_vocab_size: The vocabulary size of the `token_type_ids` passed into
-                `BertModel`.
-            initializer_range: The sttdev of the truncated_normal_initializer for
-                initializing all weight matrices.
-            layer_norm_eps: The epsilon used by LayerNorm.
-        """
         super(BertConfig, self).__init__(**kwargs)
         if isinstance(vocab_size_or_config_json_file, str) or (sys.version_info[0] == 2
                         and isinstance(vocab_size_or_config_json_file, unicode)):