sg&ddlmZGddeZy))PretrainedConfigcLeZdZdZdZ dfd ZxZS) NezhaConfiga This is the configuration class to store the configuration of an [`NezhaModel`]. It is used to instantiate an Nezha 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 Nezha [sijunhe/nezha-cn-base](https://huggingface.co/sijunhe/nezha-cn-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 21128): Vocabulary size of the NEZHA model. Defines the different tokens that can be represented by the *inputs_ids* passed to the forward method of [`NezhaModel`]. 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): The 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. 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 (e.g., 512 or 1024 or 2048). type_vocab_size (`int`, optional, defaults to 2): The vocabulary size of the *token_type_ids* passed into [`NezhaModel`]. 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. classifier_dropout (`float`, optional, defaults to 0.1): The dropout ratio for attached classifiers. is_decoder (`bool`, *optional*, defaults to `False`): Whether the model is used as a decoder or not. If `False`, the model is used as an encoder. Example: ```python >>> from transformers import NezhaConfig, NezhaModel >>> # Initializing an Nezha configuration >>> configuration = NezhaConfig() >>> # Initializing a model (with random weights) from the Nezha-base style configuration model >>> model = NezhaModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```nezhac t|d|||d|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_y)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_size hidden_sizenum_hidden_layersnum_attention_heads hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingsmax_relative_positiontype_vocab_sizeinitializer_rangelayer_norm_epsclassifier_dropout use_cache)selfrrrrrrrrrrrrrrrr r rkwargs __class__s k/var/www/html/venv/lib/python3.12/site-packages/transformers/models/deprecated/nezha/configuration_nezha.pyr zNezhaConfig.__init__@s, sl\hslrs$&!2#6 $!2#6 ,H)'>$%:".!2,"4")iRi r"i gelu皙?r$i@g{Gz?g-q=r$r&T)__name__ __module__ __qualname____doc__ model_typer __classcell__)rs@r rrsR7 rJ%( # '&#&#r!rN)rrr r!r r0s!b#"b#r!