U &ºcnã@sJdZddlZddlmZe e¡Zddddd d d d œZGd d„deƒZdS)z DistilBERT model configuration éNé)ÚPretrainedConfigzWhttps://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-uncased-config.jsonzghttps://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-uncased-distilled-squad-config.jsonzUhttps://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-cased-config.jsonzehttps://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-cased-distilled-squad-config.jsonz\https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-german-cased-config.jsonzbhttps://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-multilingual-cased-config.jsonzohttps://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-uncased-finetuned-sst-2-english-config.json)zdistilbert-base-uncasedz'distilbert-base-uncased-distilled-squadzdistilbert-base-casedz%distilbert-base-cased-distilled-squadzdistilbert-base-german-casedz"distilbert-base-multilingual-casedz/distilbert-base-uncased-finetuned-sst-2-englishcsNeZdZdZeZdZd‡fdd„ Zedd„ƒZ edd„ƒZ edd„ƒZ ‡Z S)ÚDistilBertConfiga« This is the configuration class to store the configuration of a :class:`~transformers.DistilBertModel`. It is used to instantiate a DistilBERT 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 DistilBERT `distilbert-base-uncased `__ 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 DistilBERT model. Defines the different tokens that can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.BertModel`. 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). sinusoidal_pos_embds (:obj:`boolean`, optional, defaults to :obj:`False`): Whether to use sinusoidal positional embeddings. n_layers (:obj:`int`, optional, defaults to 6): Number of hidden layers in the Transformer encoder. n_heads (:obj:`int`, optional, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. dim (:obj:`int`, optional, defaults to 768): Dimensionality of the encoder layers and the pooler layer. hidden_dim (:obj:`int`, optional, defaults to 3072): The size of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. dropout (:obj:`float`, optional, defaults to 0.1): The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler. attention_dropout (:obj:`float`, optional, defaults to 0.1): The dropout ratio for the attention probabilities. activation (: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. initializer_range (:obj:`float`, optional, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. qa_dropout (:obj:`float`, optional, defaults to 0.1): The dropout probabilities used in the question answering model :class:`~tranformers.DistilBertForQuestionAnswering`. seq_classif_dropout (:obj:`float`, optional, defaults to 0.2): The dropout probabilities used in the sequence classification model :class:`~tranformers.DistilBertForSequenceClassification`. Example:: from transformers import DistilBertModel, DistilBertConfig # Initializing a DistilBERT configuration configuration = DistilBertConfig() # Initializing a model from the configuration model = DistilBertModel(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. Z distilberté:wéFéé éé çš™™™™™¹?Úgeluç{®Gáz”?çš™™™™™É?rc shtƒjf|d|i—Ž||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_dS)NÚ pad_token_id)ÚsuperÚ__init__Ú vocab_sizeÚmax_position_embeddingsÚsinusoidal_pos_embdsÚn_layersÚn_headsÚdimÚ hidden_dimÚdropoutÚattention_dropoutÚ activationÚinitializer_rangeÚ qa_dropoutÚseq_classif_dropout)ÚselfrrrrrrrrrrrrrrÚkwargs©Ú __class__©úI/tmp/pip-unpacked-wheel-ymerj3tt/transformers/configuration_distilbert.pyreszDistilBertConfig.__init__cCs|jS©N)r©rr#r#r$Ú hidden_size†szDistilBertConfig.hidden_sizecCs|jSr%)rr&r#r#r$Únum_attention_headsŠsz$DistilBertConfig.num_attention_headscCs|jSr%)rr&r#r#r$Únum_hidden_layersŽsz"DistilBertConfig.num_hidden_layers)rrFrrr r r r r r r rr) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú(DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAPZpretrained_config_archive_mapZ model_typerÚpropertyr'r(r)Ú __classcell__r#r#r!r$r$s0=ñ!  r) r-ÚloggingZconfiguration_utilsrÚ getLoggerr*Úloggerr.rr#r#r#r$Ús  ù