U &ºc£ã@sHdZddlZddlmZe e¡Zddddd d d œZGd d „d eƒZdS)z ELECTRA model configuration éNé)ÚPretrainedConfigz^https://s3.amazonaws.com/models.huggingface.co/bert/google/electra-small-generator/config.jsonz]https://s3.amazonaws.com/models.huggingface.co/bert/google/electra-base-generator/config.jsonz^https://s3.amazonaws.com/models.huggingface.co/bert/google/electra-large-generator/config.jsonzbhttps://s3.amazonaws.com/models.huggingface.co/bert/google/electra-small-discriminator/config.jsonzahttps://s3.amazonaws.com/models.huggingface.co/bert/google/electra-base-discriminator/config.jsonzbhttps://s3.amazonaws.com/models.huggingface.co/bert/google/electra-large-discriminator/config.json)zgoogle/electra-small-generatorzgoogle/electra-base-generatorzgoogle/electra-large-generatorz"google/electra-small-discriminatorz!google/electra-base-discriminatorz"google/electra-large-discriminatorcs*eZdZdZeZdZd‡fdd„ Z‡ZS)Ú ElectraConfiga› This is the configuration class to store the configuration of a :class:`~transformers.ElectraModel`. It is used to instantiate an ELECTRA model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the ELECTRA `google/electra-small-discriminator `__ architecture. Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information. Args: vocab_size (:obj:`int`, optional, defaults to 30522): Vocabulary size of the ELECTRA model. Defines the different tokens that can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.ElectraModel`. embedding_size (:obj:`int`, optional, defaults to 128): Dimensionality of the encoder layers and the pooler layer. hidden_size (:obj:`int`, optional, defaults to 256): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (:obj:`int`, optional, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (:obj:`int`, optional, defaults to 4): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (:obj:`int`, optional, defaults to 1024): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. hidden_act (:obj:`str` or :obj:`function`, optional, defaults to "gelu"): The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "swish" and "gelu_new" are supported. hidden_dropout_prob (:obj:`float`, optional, defaults to 0.1): The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (:obj:`float`, optional, defaults to 0.1): The dropout ratio for the attention probabilities. max_position_embeddings (:obj:`int`, optional, defaults to 512): 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 (:obj:`int`, optional, defaults to 2): The vocabulary size of the `token_type_ids` passed into :class:`~transformers.ElectraModel`. initializer_range (:obj:`float`, optional, defaults to 0.02): 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 ElectraModel, ElectraConfig # Initializing a ELECTRA electra-base-uncased style configuration configuration = ElectraConfig() # Initializing a model from the electra-base-uncased style configuration model = ElectraModel(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. Zelectraé:wé€éé ééÚgeluçš™™™™™¹?ééç{®Gáz”?çê-™—q=rc shtƒjfd|i|—Ž||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_dS)NÚ pad_token_id)ÚsuperÚ__init__Ú vocab_sizeÚembedding_sizeÚ hidden_sizeÚnum_hidden_layersÚnum_attention_headsÚintermediate_sizeÚ hidden_actÚhidden_dropout_probÚattention_probs_dropout_probÚmax_position_embeddingsÚtype_vocab_sizeÚinitializer_rangeÚlayer_norm_eps)Úselfrrrrrrrrrrrrr rÚkwargs©Ú __class__©úF/tmp/pip-unpacked-wheel-ymerj3tt/transformers/configuration_electra.pyrdszElectraConfig.__init__)rrrrr r r r r r rrrr) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú%ELECTRA_PRETRAINED_CONFIG_ARCHIVE_MAPZpretrained_config_archive_mapZ model_typerÚ __classcell__r%r%r#r&r$s$<ñr) r*ÚloggingZconfiguration_utilsrÚ getLoggerr'Úloggerr+rr%r%r%r&Ús  ú