sg1ZdZddlmZddlmZej eZGddeZy)zSalesforce CTRL configuration)PretrainedConfig)loggingcReZdZdZdZdgZdddddZ d fd ZxZS) CTRLConfiga This is the configuration class to store the configuration of a [`CTRLModel`] or a [`TFCTRLModel`]. It is used to instantiate a 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 [Salesforce/ctrl](https://huggingface.co/Salesforce/ctrl) architecture from SalesForce. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 246534): Vocabulary size of the CTRL model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`CTRLModel`] or [`TFCTRLModel`]. n_positions (`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_embd (`int`, *optional*, defaults to 1280): Dimensionality of the embeddings and hidden states. dff (`int`, *optional*, defaults to 8192): Dimensionality of the inner dimension of the feed forward networks (FFN). n_layer (`int`, *optional*, defaults to 48): Number of hidden layers in the Transformer encoder. n_head (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. resid_pdrop (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. embd_pdrop (`int`, *optional*, defaults to 0.1): The dropout ratio for the embeddings. layer_norm_epsilon (`float`, *optional*, defaults to 1e-06): The epsilon to use in the layer normalization layers initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Examples: ```python >>> from transformers import CTRLConfig, CTRLModel >>> # Initializing a CTRL configuration >>> configuration = CTRLConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = CTRLModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ctrlpast_key_values n_positionsn_embdn_headn_layer)max_position_embeddings hidden_sizenum_attention_headsnum_hidden_layersc  ||_||_||_||_||_||_||_||_| |_| |_ | |_ t |0di| y)N) vocab_sizer r r r dff resid_pdrop embd_pdroplayer_norm_epsiloninitializer_range use_cachesuper__init__)selfrr r rr r rrrrrkwargs __class__s ^/var/www/html/venv/lib/python3.12/site-packages/transformers/models/ctrl/configuration_ctrl.pyrzCTRLConfig.__init__Usf%&   &$"4!2" "6") iii 0皙?r$gư>g{Gz?T) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr __classcell__)rs@rrrsY1 fJ#4"5#0'& M ##r rN) r(configuration_utilsrutilsr get_loggerr%loggerrrr rr1s3$3   H %Y#!Y#r