fThSrSSKJr SSKJr SSKJr SSKJr SSK J r \ R"\ 5r "SS \5r"S S \5rS S /rg ) zConvBERT model configuration) OrderedDict)Mapping)PretrainedConfig) OnnxConfig)loggingc\^\rSrSrSrSrSU4SjjrSrU=r$)ConvBertConfiga This is the configuration class to store the configuration of a [`ConvBertModel`]. It is used to instantiate an ConvBERT 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 ConvBERT [YituTech/conv-bert-base](https://huggingface.co/YituTech/conv-bert-base) 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 ConvBERT model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`ConvBertModel`] or [`TFConvBertModel`]. 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" (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 [`ConvBertModel`] or [`TFConvBertModel`]. 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. head_ratio (`int`, *optional*, defaults to 2): Ratio gamma to reduce the number of attention heads. num_groups (`int`, *optional*, defaults to 1): The number of groups for grouped linear layers for ConvBert model conv_kernel_size (`int`, *optional*, defaults to 9): The size of the convolutional kernel. classifier_dropout (`float`, *optional*): The dropout ratio for the classification head. Example: ```python >>> from transformers import ConvBertConfig, ConvBertModel >>> # Initializing a ConvBERT convbert-base-uncased style configuration >>> configuration = ConvBertConfig() >>> # Initializing a model (with random weights) from the convbert-base-uncased style configuration >>> model = ConvBertModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```convbertc >[TU]"SU UUS.UD6 XlX lX0lX@lXPlX`lXplXl Xl Xl Xl Xl UUlUUlUUlUUlUUlg)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_size hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_epsembedding_size head_ratioconv_kernel_size num_groupsclassifier_dropout)selfrrrrrrrrrrrrrrrr r!r"r#r$kwargs __class__s k/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/convbert/configuration_convbert.pyrConvBertConfig.__init__]s0  %%%   %&!2#6 !2$#6 ,H)'>$.!2,,$ 0$"4)rr$r"r r!rrrrrrrrr#rrr)i:w r,i gelu皙?r.ig{Gz?g-q=rr/r+r/ r0N) __name__ __module__ __qualname____firstlineno____doc__ model_typer__static_attributes__ __classcell__)r's@r(r r sX< |J%( #+/5/5r*r c@\rSrSr\S\\\\\444Sj5rSr g)ConvBertOnnxConfigreturncbURS:XaSSSS.nOSSS.n[SU4SU4S U4/5$) Nzmultiple-choicebatchchoicesequence)rr0r/)rr0 input_idsattention_masktoken_type_ids)taskr)r% dynamic_axiss r(inputsConvBertOnnxConfig.inputssO 99) )&8 CL&:6Ll+!<0!<0   r*rN) r2r3r4r5propertyrstrintrGr8rr*r(r;r;s.   WS#X%6 67    r*r;N)r6 collectionsrtypingrconfiguration_utilsronnxrutilsr get_loggerr2loggerr r;__all__rr*r(rTsT##3   H %p5%p5h    1 2r*