qi `dZddlmZddlmZej eZGddeZdgZ y)zDistilBERT model configuration)PreTrainedConfig)loggingcVeZdZdZdZddddZ dfd ZxZS) DistilBertConfiga This is the configuration class to store the configuration of a [`DistilBertModel`]. It is used to instantiate a DistilBERT 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 DistilBERT [distilbert-base-uncased](https://huggingface.co/distilbert-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 DistilBERT model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`DistilBertModel`]. 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). sinusoidal_pos_embds (`boolean`, *optional*, defaults to `False`): Whether to use sinusoidal positional embeddings. n_layers (`int`, *optional*, defaults to 6): Number of hidden layers in the Transformer encoder. n_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. dim (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. hidden_dim (`int`, *optional*, defaults to 3072): The size of the "intermediate" (often named feed-forward) layer in the Transformer encoder. dropout (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. activation (`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. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. qa_dropout (`float`, *optional*, defaults to 0.1): The dropout probabilities used in the question answering model [`DistilBertForQuestionAnswering`]. seq_classif_dropout (`float`, *optional*, defaults to 0.2): The dropout probabilities used in the sequence classification and the multiple choice model [`DistilBertForSequenceClassification`]. Examples: ```python >>> from transformers import DistilBertConfig, DistilBertModel >>> # Initializing a DistilBERT configuration >>> configuration = DistilBertConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = DistilBertModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` distilbertdimn_headsn_layers) hidden_sizenum_attention_headsnum_hidden_layersc ||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_||_t#|Hdi|y)N) vocab_sizemax_position_embeddingssinusoidal_pos_embdsr r r hidden_dimdropoutattention_dropout activationinitializer_range qa_dropoutseq_classif_dropout pad_token_id eos_token_id bos_token_idtie_word_embeddingssuper__init__)selfrrrr r rrrrrrrrrrrrkwargs __class__s i/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/distilbert/configuration_distilbert.pyrzDistilBertConfig.__init__Ws*%'>$$8!   $ !2$!2$#6 (((#6  "6")i:wiF ii 皙?r'gelug{Gz?r'g?NNT)__name__ __module__ __qualname____doc__ model_type attribute_mapr __classcell__)r"s@r#rrs_6 pJ('M #"  %&#&#r$rN) r-configuration_utilsrutilsr get_loggerr*loggerr__all__rr$r#r6s>%3   H %f#'f#R  r$