o ei@s@dZddlmZddlmZeeZGdddeZdgZ dS)zSalesforce CTRL configuration)PreTrainedConfig)loggingcsXeZdZdZdZdgZdddddZ          dfdd ZZS) CTRLConfiga This is the configuration class to store the configuration of a [`CTRLModel`]. 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`]. 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). pad_token_id (`int`, *optional*): Padding token id. bos_token_id (`int`, *optional*): Beginning of stream token id. eos_token_id (`int`, *optional*): End of stream token id. tie_word_embeddings (`bool`, *optional*, defaults to `True`): Whether to tie weight embeddings 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_layers 0皙?ư>{Gz?TNc sp||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ ||_ ||_ | |_tjdi|dS)N) vocab_sizerrr r dff resid_pdrop embd_pdroplayer_norm_epsiloninitializer_range pad_token_id bos_token_id eos_token_idtie_word_embeddings use_cachesuper__init__)selfrrrrr r rrrrr#rr r!r"kwargs __class__ri/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/ctrl/configuration_ctrl.pyr%\s zCTRLConfig.__init__)rrrrrrrrrrTNNNT) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr% __classcell__rrr(r*rs2; rN) r.configuration_utilsrutilsr get_loggerr+loggerr__all__rrrr*s     l