o ei@s@dZddlmZddlmZeeZGdddeZdgZ dS)zELECTRA model configuration)PreTrainedConfig)loggingcsXeZdZdZdZ                 dfdd ZZS) ElectraConfiga This is the configuration class to store the configuration of a [`ElectraModel`]. It is used to instantiate a ELECTRA 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 ELECTRA [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) architecture. 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 30522): Vocabulary size of the ELECTRA model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`ElectraModel`]. embedding_size (`int`, *optional*, defaults to 128): Dimensionality of the encoder layers and the pooler layer. hidden_size (`int`, *optional*, defaults to 256): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 4): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 1024): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. max_position_embeddings (`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). type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the `token_type_ids` passed when calling [`ElectraModel`]. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. summary_type (`str`, *optional*, defaults to `"first"`): Argument used when doing sequence summary. Used in the sequence classification and multiple choice models. Has to be 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 (like GPT/GPT-2). - `"attn"`: Not implemented now, use multi-head attention. summary_use_proj (`bool`, *optional*, defaults to `True`): Argument used when doing sequence summary. Used in the sequence classification and multiple choice models. Whether or not to add a projection after the vector extraction. summary_activation (`str`, *optional*): Argument used when doing sequence summary. Used in the sequence classification and multiple choice models. Pass `"gelu"` for a gelu activation to the output, any other value will result in no activation. summary_last_dropout (`float`, *optional*, defaults to 0.0): Argument used when doing sequence summary. Used in the sequence classification and multiple choice models. The dropout ratio to be used after the projection and activation. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. classifier_dropout (`float`, *optional*): The dropout ratio for the classification head. Examples: ```python >>> from transformers import ElectraConfig, ElectraModel >>> # Initializing a ELECTRA electra-base-uncased style configuration >>> configuration = ElectraConfig() >>> # Initializing a model (with random weights) from the electra-base-uncased style configuration >>> model = ElectraModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```electra:w gelu皙?{Gz?-q=firstTNFc stjdi|||_||_||_||_||_||_||_||_ ||_ ||_ ||_ ||_ ||_||_| |_| |_| |_| |_| |_||_||_||_||_||_||_dS)N)super__init__ pad_token_id bos_token_id eos_token_idtie_word_embeddings is_decoderadd_cross_attention vocab_sizeembedding_size hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_eps summary_typesummary_use_projsummary_activationsummary_last_dropout use_cacheclassifier_dropout)selfrrrr r!r"r#r$r%r&r'r(r)r*r+r,r-rr.r/rrrrrkwargs __class__ro/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/electra/configuration_electra.pyrns4 zElectraConfig.__init__)rrrr r r r r r rrrrrTr r rTNFFNNT)__name__ __module__ __qualname____doc__ model_typer __classcell__rrr2r4rs:SrN) r8configuration_utilsrutilsr get_loggerr5loggerr__all__rrrr4s