sgZdZddlmZddlmZej eZGddeZy)zMPNet model configuration)PretrainedConfig)loggingcFeZdZdZdZ dfd ZxZS) MPNetConfiga" This is the configuration class to store the configuration of a [`MPNetModel`] or a [`TFMPNetModel`]. It is used to instantiate a MPNet 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 MPNet [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-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 30527): Vocabulary size of the MPNet model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`MPNetModel`] or [`TFMPNetModel`]. 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" (often named feed-forward) layer in the Transformer encoder. hidden_act (`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. 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). 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. relative_attention_num_buckets (`int`, *optional*, defaults to 32): The number of buckets to use for each attention layer. Examples: ```python >>> from transformers import MPNetModel, MPNetConfig >>> # Initializing a MPNet mpnet-base style configuration >>> configuration = MPNetConfig() >>> # Initializing a model from the mpnet-base style configuration >>> model = MPNetModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```mpnetc 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_embeddingsinitializer_rangelayer_norm_epsrelative_attention_num_buckets)selfrrrrrrrrrrrrr r r kwargs __class__s `/var/www/html/venv/lib/python3.12/site-packages/transformers/models/mpnet/configuration_mpnet.pyrzMPNetConfig.__init__Qs~& sl\hslrs$&!2#6 $!2#6 ,H)'>$!2,.L+)i?wi r i gelu皙?r"ig{Gz?g-q= )__name__ __module__ __qualname____doc__ model_typer __classcell__)rs@rrrsK3 jJ%( #')! M MrrN) r*configuration_utilsrutilsr get_loggerr'loggerrr rrr1s5  3   H %XM"XMr