U &c@s>dZddlZddlmZeeZddiZGdddeZdS) z Salesforce CTRL configuration N)PretrainedConfigctrlz?https://storage.googleapis.com/sf-ctrl/pytorch/ctrl-config.jsoncsZeZdZdZeZdZdfdd ZeddZ eddZ eddZ eddZ Z S) CTRLConfiga> This is the configuration class to store the configuration of an :class:`~transformers.CTRLModel`. It is used to instantiate an CTRL 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 `ctrl `__ architecture from SalesForce. 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 246534): Vocabulary size of the CTRL model. Defines the different tokens that can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.CTRLModel`. n_positions (:obj:`int`, optional, defaults to 256): 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). n_ctx (:obj:`int`, optional, defaults to 256): Dimensionality of the causal mask (usually same as n_positions). n_embd (:obj:`int`, optional, defaults to 1280): Dimensionality of the embeddings and hidden states. dff (:obj:`int`, optional, defaults to 8192): Dimensionality of the inner dimension of the FFN. n_layer (:obj:`int`, optional, defaults to 48): 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. resid_pdrop (:obj:`float`, optional, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. embd_pdrop (:obj:`int`, optional, defaults to 0.1): The dropout ratio for the embeddings. attn_pdrop (:obj:`float`, optional, defaults to 0.1): The dropout ratio for the attention. layer_norm_epsilon (:obj:`float`, optional, defaults to 1e-6): The epsilon to use in the layer normalization layers initializer_range (:obj:`float`, optional, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. Example:: from transformers import CTRLModel, CTRLConfig # Initializing a CTRL configuration configuration = CTRLConfig() # Initializing a model from the configuration model = CTRLModel(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. r 0皙?ư>{Gz? cls_indexTNc sxtjf|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_||_dSN)super__init__ vocab_sizen_ctx n_positionsn_embdn_layern_headdff resid_pdrop embd_pdrop attn_pdroplayer_norm_epsiloninitializer_range summary_typesummary_use_projsummary_activationsummary_first_dropoutsummary_proj_to_labels)selfrrrrrrrrrrrrrr r!r#r"kwargs __class__C/tmp/pip-unpacked-wheel-ymerj3tt/transformers/configuration_ctrl.pyrXs$zCTRLConfig.__init__cCs|jSr)rr$r(r(r)max_position_embeddingssz"CTRLConfig.max_position_embeddingscCs|jSr)rr*r(r(r) hidden_sizeszCTRLConfig.hidden_sizecCs|jSr)rr*r(r(r)num_attention_headsszCTRLConfig.num_attention_headscCs|jSr)rr*r(r(r)num_hidden_layersszCTRLConfig.num_hidden_layers)rrrrr r r r r r r rrTNTr )__name__ __module__ __qualname____doc__"CTRL_PRETRAINED_CONFIG_ARCHIVE_MAPZpretrained_config_archive_mapZ model_typerpropertyr+r,r-r. __classcell__r(r(r&r)rs:8)   r) r2loggingZconfiguration_utilsr getLoggerr/loggerr3rr(r(r(r)s