o ei@s@dZddlmZddlmZeeZGdddeZdgZ dS)zConvBERT model configuration)PreTrainedConfig)loggingcsTeZdZdZdZ               dfdd ZZS)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`]. 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`]. 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 ```convbert:w gelu皙?{Gz?-q= NFTc stjdi|| |_||_||_||_||_||_||_||_ ||_ ||_ ||_ ||_ ||_||_| |_| |_| |_| |_||_||_||_||_||_dS)N)super__init__ pad_token_id bos_token_id eos_token_idtie_word_embeddings is_decoderadd_cross_attention 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)selfrrrrr r!r"r#r$r%r&r'rrrr(r)r*r+r,rrrkwargs __class__rq/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/convbert/configuration_convbert.pyrXs0 zConvBertConfig.__init__)rrrrr r r r r r rrrrr rr rrNFFT)__name__ __module__ __qualname____doc__ model_typer __classcell__rrr/r1rs6>rN) r5configuration_utilsrutilsr get_loggerr2loggerr__all__rrrr1s     w