o ¾e¦igã@s@dZddlmZddlmZe e¡ZGdd„deƒZdgZ dS)zBERT model configurationé)ÚPreTrainedConfig)ÚloggingcsNeZdZdZdZ               d‡fdd„ Z‡ZS)Ú BertConfiga7 This is the configuration class to store the configuration of a [`BertModel`]. It is used to instantiate a BERT 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 BERT [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) 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 BERT model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`BertModel`]. hidden_size (`int`, *optional*, defaults to 768): 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 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (often named 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 [`BertModel`]. 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. is_decoder (`bool`, *optional*, defaults to `False`): Whether the model is used as a decoder or not. If `False`, the model is used as an encoder. 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 BertConfig, BertModel >>> # Initializing a BERT google-bert/bert-base-uncased style configuration >>> configuration = BertConfig() >>> # Initializing a model (with random weights) from the google-bert/bert-base-uncased style configuration >>> model = BertModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Úberté:wéé é Úgeluçš™™™™™¹?ééç{®Gáz”?çê-™—q=éTNFc sŽtƒjdi|¤Ž| |_||_||_||_||_||_||_||_ ||_ ||_ ||_ ||_ ||_||_| |_| |_| |_| |_||_||_dS)N©)ÚsuperÚ__init__Ú pad_token_idÚ is_decoderÚadd_cross_attentionÚ bos_token_idÚ eos_token_idÚtie_word_embeddingsÚ vocab_sizeÚ hidden_sizeÚnum_hidden_layersÚnum_attention_headsÚ hidden_actÚintermediate_sizeÚhidden_dropout_probÚattention_probs_dropout_probÚmax_position_embeddingsÚtype_vocab_sizeÚinitializer_rangeÚlayer_norm_epsÚ use_cacheÚclassifier_dropout)Úselfrrrrrrr r!r"r#r$r%rr&r'rrrrrÚkwargs©Ú __class__rúi/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/bert/configuration_bert.pyrXs* zBertConfig.__init__)rrrrr r r r r r rrrTNFFNNT)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typerÚ __classcell__rrr*r,rs0=ërN) r0Úconfiguration_utilsrÚutilsrÚ get_loggerr-ÚloggerrÚ__all__rrrr,Ús     p