o Zh@svdZddlmZddlmZddlmZddlmZddl m Z e e Z Gdd d eZGd d d eZd d gZd S) zDistilBERT model configuration) OrderedDict)Mapping)PretrainedConfig) OnnxConfig)loggingcsNeZdZdZdZddddZ         dfdd ZZS)DistilBertConfiga This is the configuration class to store the configuration of a [`DistilBertModel`] or a [`TFDistilBertModel`]. 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`] or [`TFDistilBertModel`]. 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 ```Z distilbertdimn_headsn_layers)Z hidden_sizeZnum_attention_headsZnum_hidden_layers:wF  皙?gelu{Gz?皙?rc sl||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ t jdi|d|idS)N pad_token_id) vocab_sizemax_position_embeddingssinusoidal_pos_embdsr r r hidden_dimdropoutattention_dropout activationinitializer_range qa_dropoutseq_classif_dropoutsuper__init__)selfrrrr r r rrrrrr r!rkwargs __class__rf/var/www/auris/lib/python3.10/site-packages/transformers/models/distilbert/configuration_distilbert.pyr#\szDistilBertConfig.__init__)r r Frrrrrrrrrrr)__name__ __module__ __qualname____doc__Z model_typeZ attribute_mapr# __classcell__rrr&r(rs,8rc@s.eZdZedeeeeefffddZdS)DistilBertOnnxConfigreturncCs6|jdkr dddd}nddd}td|fd|fgS) Nzmultiple-choicebatchchoicesequence)r)rr3Z input_idsZattention_mask)taskr)r$Z dynamic_axisrrr(inputss  zDistilBertOnnxConfig.inputsN)r)r*r+propertyrstrintr6rrrr(r.~s$r.N)r, collectionsrtypingrZconfiguration_utilsrZonnxrutilsrZ get_loggerr)loggerrr.__all__rrrr(s      b