cCiW`SrSSKJr SSKJr \R "\5r"SS\5rS/r g)zQDQBERT model configuration)PretrainedConfig)loggingcT^\rSrSrSrSrSU4SjjrSrU=r$) QDQBertConfiga This is the configuration class to store the configuration of a [`QDQBertModel`]. It is used to instantiate an QDQBERT 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 QDQBERT model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`QDQBertModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimension 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): Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` 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 [`QDQBertModel`]. 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`. Examples: ```python >>> from transformers import QDQBertModel, QDQBertConfig >>> # Initializing a QDQBERT google-bert/bert-base-uncased style configuration >>> configuration = QDQBertConfig() >>> # Initializing a model from the google-bert/bert-base-uncased style configuration >>> model = QDQBertModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```qdqbertc >[TU]"SXUS.UD6 XlXlX lX0lX@lXPlX`lXpl Xl Xl Xl Xl Xlg)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_sizemax_position_embeddings hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangetype_vocab_sizelayer_norm_eps use_cache)selfrrrrrrrrrrrrrr r r kwargs __class__s v/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/deprecated/qdqbert/configuration_qdqbert.pyrQDQBertConfig.__init__Vsi( sl\hslrs$'>$&!2#6 !2$#6 ,H)!2.,") rrrrrrrrrrrrr)i:wi r#i gelu皙?r%ig{Gz?g-q=Tr&) __name__ __module__ __qualname____firstlineno____doc__ model_typer__static_attributes__ __classcell__)rs@r rrsL9 vJ%( ##"#"#r"rN) r-configuration_utilsrutilsr get_loggerr)loggerr__all__r r"r r6s<"4   H %`#$`#F  r"