U &ºcAã @s:dZddlmZddddddd d d œZGd d „d eƒZdS)z ALBERT model configuration é)ÚPretrainedConfigzNhttps://s3.amazonaws.com/models.huggingface.co/bert/albert-base-v1-config.jsonzOhttps://s3.amazonaws.com/models.huggingface.co/bert/albert-large-v1-config.jsonzPhttps://s3.amazonaws.com/models.huggingface.co/bert/albert-xlarge-v1-config.jsonzQhttps://s3.amazonaws.com/models.huggingface.co/bert/albert-xxlarge-v1-config.jsonzNhttps://s3.amazonaws.com/models.huggingface.co/bert/albert-base-v2-config.jsonzOhttps://s3.amazonaws.com/models.huggingface.co/bert/albert-large-v2-config.jsonzPhttps://s3.amazonaws.com/models.huggingface.co/bert/albert-xlarge-v2-config.jsonzQhttps://s3.amazonaws.com/models.huggingface.co/bert/albert-xxlarge-v2-config.json)zalbert-base-v1zalbert-large-v1zalbert-xlarge-v1zalbert-xxlarge-v1zalbert-base-v2zalbert-large-v2zalbert-xlarge-v2zalbert-xxlarge-v2cs*eZdZdZeZdZd‡fdd„ Z‡ZS)Ú AlbertConfigaù This is the configuration class to store the configuration of an :class:`~transformers.AlbertModel`. It is used to instantiate an ALBERT 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 ALBERT `xxlarge `__ 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 30000): Vocabulary size of the ALBERT model. Defines the different tokens that can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.AlbertModel`. embedding_size (:obj:`int`, optional, defaults to 128): Dimensionality of vocabulary embeddings. hidden_size (:obj:`int`, optional, defaults to 4096): 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_hidden_groups (:obj:`int`, optional, defaults to 1): Number of groups for the hidden layers, parameters in the same group are shared. num_attention_heads (:obj:`int`, optional, defaults to 64): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (:obj:`int`, optional, defaults to 16384): The dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. inner_group_num (:obj:`int`, optional, defaults to 1): The number of inner repetition of attention and ffn. hidden_act (:obj:`str` or :obj:`function`, optional, defaults to "gelu_new"): 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): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (:obj:`float`, optional, defaults to 0): 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 (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.AlbertModel`. 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. classifier_dropout_prob (:obj:`float`, optional, defaults to 0.1): The dropout ratio for attached classifiers. Example:: from transformers import AlbertConfig, AlbertModel # Initializing an ALBERT-xxlarge style configuration albert_xxlarge_configuration = AlbertConfig() # Initializing an ALBERT-base style configuration albert_base_configuration = AlbertConfig( hidden_size=768, num_attention_heads=12, intermediate_size=3072, ) # Initializing a model from the ALBERT-base style configuration model = AlbertModel(albert_xxlarge_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. Zalberté0ué€éé ré@é@Úgelu_newéééç{®Gáz”?çê-™—q=çš™™™™™¹?éc s~tƒjf|||dœ|—Ž||_||_||_||_||_||_||_| |_ ||_ | |_ | |_ | |_ | |_||_||_||_dS)N)Ú pad_token_idÚ bos_token_idÚ eos_token_id)ÚsuperÚ__init__Ú vocab_sizeÚembedding_sizeÚ hidden_sizeÚnum_hidden_layersÚnum_hidden_groupsÚnum_attention_headsÚinner_group_numÚ hidden_actÚintermediate_sizeÚhidden_dropout_probÚattention_probs_dropout_probÚmax_position_embeddingsÚtype_vocab_sizeÚinitializer_rangeÚlayer_norm_epsÚclassifier_dropout_prob)Úselfrrrrrrrrrr r!r"r#r$r%r&rrrÚkwargs©Ú __class__©úE/tmp/pip-unpacked-wheel-ymerj3tt/transformers/configuration_albert.pyrms"zAlbertConfig.__init__)rrrrrrr rr r r r r rrrr r r) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú$ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAPZpretrained_config_archive_mapZ model_typerÚ __classcell__r+r+r)r,r!s.HìrN)r0Zconfiguration_utilsrr1rr+r+r+r,Ús ø