o ¾e¦i ã@s@dZddlmZddlmZe e¡ZGdd„deƒZdgZ dS)zDistilBERT model configurationé)ÚPreTrainedConfig)ÚloggingcsTeZdZdZdZddddœZ            d‡fdd„ Z‡ZS)ÚDistilBertConfigaå 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 ```Ú distilbertÚdimÚn_headsÚn_layers)Ú hidden_sizeÚnum_attention_headsÚnum_hidden_layersé:wéFéé éé çš™™™™™¹?Úgeluç{®Gáz”?çš™™™™™É?éNTc s|||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_||_tƒjdi|¤ŽdS)N©)Ú vocab_sizeÚmax_position_embeddingsÚsinusoidal_pos_embdsrrrÚ hidden_dimÚdropoutÚattention_dropoutÚ activationÚinitializer_rangeÚ qa_dropoutÚseq_classif_dropoutÚ pad_token_idÚ eos_token_idÚ bos_token_idÚtie_word_embeddingsÚsuperÚ__init__)Úselfrrrrrrrrrrrr r!r"r#r$r%Úkwargs©Ú __class__rúu/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/distilbert/configuration_distilbert.pyr'Ws$zDistilBertConfig.__init__)r r FrrrrrrrrrrrNNT)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚ attribute_mapr'Ú __classcell__rrr*r,rs28ýîrN) r0Úconfiguration_utilsrÚutilsrÚ get_loggerr-ÚloggerrÚ__all__rrrr,Ús     i