U &c)@s@dZddlZddlmZeeZdddZGdd d eZdS) z XLNet configuration N)PretrainedConfigzPhttps://s3.amazonaws.com/models.huggingface.co/bert/xlnet-base-cased-config.jsonzQhttps://s3.amazonaws.com/models.huggingface.co/bert/xlnet-large-cased-config.json)zxlnet-base-casedzxlnet-large-casedcsteZdZdZeZdZd#fdd ZeddZ eddZ e j ddZ eddZ edd Z ed!d"ZZS)$ XLNetConfiga This is the configuration class to store the configuration of a :class:`~transformers.XLNetModel`. It is used to instantiate an XLNet 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 `xlnet-large-cased `__ 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 32000): Vocabulary size of the XLNet model. Defines the different tokens that can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.XLNetModel`. d_model (:obj:`int`, optional, defaults to 1024): Dimensionality of the encoder layers and the pooler layer. n_layer (:obj:`int`, optional, defaults to 24): Number of hidden layers in the Transformer encoder. n_head (:obj:`int`, optional, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. d_inner (:obj:`int`, optional, defaults to 4096): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. ff_activation (:obj:`string`, optional, defaults to "gelu"): The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu" and "swish" are supported. untie_r (:obj:`boolean`, optional, defaults to :obj:`True`): Untie relative position biases attn_type (:obj:`string`, optional, defaults to "bi"): The attention type used by the model. Set 'bi' for XLNet, 'uni' for Transformer-XL. 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. dropout (:obj:`float`, optional, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. mem_len (:obj:`int` or :obj:`None`, optional, defaults to :obj:`None`): The number of tokens to cache. The key/value pairs that have already been pre-computed in a previous forward pass won't be re-computed. See the `quickstart `__ for more information. reuse_len (:obj:`int` or :obj:`None`, optional, defaults to :obj:`None`): The number of tokens in the current batch to be cached and reused in the future. bi_data (:obj:`boolean`, optional, defaults to :obj:`False`): Whether to use bidirectional input pipeline. Usually set to `True` during pretraining and `False` during finetuning. clamp_len (:obj:`int`, optional, defaults to -1): Clamp all relative distances larger than clamp_len. Setting this attribute to -1 means no clamping. same_length (:obj:`boolean`, optional, defaults to :obj:`False`): Whether to use the same attention length for each token. summary_type (:obj:`string`, optional, defaults to "last"): Argument used when doing sequence summary. Used in for the multiple choice head in :class:transformers.XLNetForSequenceClassification` and :class:`~transformers.XLNetForMultipleChoice`. Is one of the following options: - 'last' => take the last token hidden state (like XLNet) - 'first' => take the first token hidden state (like Bert) - 'mean' => take the mean of all tokens hidden states - 'cls_index' => supply a Tensor of classification token position (GPT/GPT-2) - 'attn' => Not implemented now, use multi-head attention summary_use_proj (:obj:`boolean`, optional, defaults to :obj:`True`): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.XLNetForSequenceClassification` and :class:`~transformers.XLNetForMultipleChoice`. Add a projection after the vector extraction summary_activation (:obj:`string` or :obj:`None`, optional, defaults to :obj:`None`): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.XLNetForSequenceClassification` and :class:`~transformers.XLNetForMultipleChoice`. 'tanh' => add a tanh activation to the output, Other => no activation. summary_proj_to_labels (:obj:`boolean`, optional, defaults to :obj:`True`): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.XLNetForSequenceClassification` and :class:`~transformers.XLNetForMultipleChoice`. If True, the projection outputs to config.num_labels classes (otherwise to hidden_size). Default: False. summary_last_dropout (:obj:`float`, optional, defaults to 0.1): Argument used when doing sequence summary. Used in for the multiple choice head in :class:`~transformers.XLNetForSequenceClassification` and :class:`~transformers.XLNetForMultipleChoice`. Add a dropout after the projection and activation start_n_top (:obj:`int`, optional, defaults to 5): Used in the SQuAD evaluation script for XLM and XLNet. end_n_top (:obj:`int`, optional, defaults to 5): Used in the SQuAD evaluation script for XLM and XLNet. Example:: from transformers import XLNetConfig, XLNetModel # Initializing a XLNet configuration configuration = XLNetConfig() # Initializing a model from the configuration model = XLNetModel(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. Zxlnet}geluTbi{Gz?-q=皙?NFlasttanhrc stjf|||d|||_||_||_||_||dksBt|||_||_||_ ||_ ||_ | |_ | |_ | |_| |_| |_||_||_||_||_||_||_||_||_||_||_||_||_dS)z Constructs XLNetConfig. ) pad_token_id bos_token_id eos_token_idrN)super__init__ vocab_sized_modeln_layern_headAssertionErrorZd_head ff_activationd_inneruntie_r attn_typeinitializer_rangelayer_norm_epsdropoutmem_len reuse_lenbi_data clamp_len same_length summary_typesummary_use_projsummary_activationsummary_last_dropout start_n_top end_n_toprrr)selfrrrrrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/rrrkwargs __class__D/tmp/pip-unpacked-wheel-ymerj3tt/transformers/configuration_xlnet.pyrs8 zXLNetConfig.__init__cCsdS)Nrr4r0r4r4r5max_position_embeddingssz#XLNetConfig.max_position_embeddingscCs|jSNrr6r4r4r5n_tokenszXLNetConfig.n_tokencCs ||_dSr8r9)r0valuer4r4r5r:scCs|jSr8)rr6r4r4r5 hidden_sizeszXLNetConfig.hidden_sizecCs|jSr8)rr6r4r4r5num_attention_headsszXLNetConfig.num_attention_headscCs|jSr8)rr6r4r4r5num_hidden_layersszXLNetConfig.num_hidden_layers)rrrrr r Tr r r rNNFrFrTrrrrrrr)__name__ __module__ __qualname____doc__#XLNET_PRETRAINED_CONFIG_ARCHIVE_MAPZpretrained_config_archive_mapZ model_typerpropertyr7r:setterr<r=r> __classcell__r4r4r2r5r sRb@     r) rBloggingZconfiguration_utilsr getLoggerr?loggerrCrr4r4r4r5s