T^(hR dZddlmZddlmZddlmZddlmZddl m Z e je Z Gdd eZGd d eZd d gZy ) zMobileBERT model configuration) OrderedDict)Mapping)PretrainedConfig) OnnxConfig)loggingcVeZdZdZdZ dfd ZxZS)MobileBertConfiga This is the configuration class to store the configuration of a [`MobileBertModel`] or a [`TFMobileBertModel`]. It is used to instantiate a MobileBERT 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 MobileBERT [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-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 MobileBERT model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`MobileBertModel`] or [`TFMobileBertModel`]. hidden_size (`int`, *optional*, defaults to 512): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 24): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 4): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 512): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"relu"`): 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 0.0): 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 [`MobileBertModel`] or [`TFMobileBertModel`]. 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. pad_token_id (`int`, *optional*, defaults to 0): The ID of the token in the word embedding to use as padding. embedding_size (`int`, *optional*, defaults to 128): The dimension of the word embedding vectors. trigram_input (`bool`, *optional*, defaults to `True`): Use a convolution of trigram as input. use_bottleneck (`bool`, *optional*, defaults to `True`): Whether to use bottleneck in BERT. intra_bottleneck_size (`int`, *optional*, defaults to 128): Size of bottleneck layer output. use_bottleneck_attention (`bool`, *optional*, defaults to `False`): Whether to use attention inputs from the bottleneck transformation. key_query_shared_bottleneck (`bool`, *optional*, defaults to `True`): Whether to use the same linear transformation for query&key in the bottleneck. num_feedforward_networks (`int`, *optional*, defaults to 4): Number of FFNs in a block. normalization_type (`str`, *optional*, defaults to `"no_norm"`): The normalization type in MobileBERT. classifier_dropout (`float`, *optional*): The dropout ratio for the classification head. Examples: ```python >>> from transformers import MobileBertConfig, MobileBertModel >>> # Initializing a MobileBERT configuration >>> configuration = MobileBertConfig() >>> # Initializing a model (with random weights) from the configuration above >>> model = MobileBertModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` mobilebertc t|dd| i|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_||_||_||_||_||_||_||_|j r||_||_y||_||_y)N pad_token_id)super__init__ vocab_size hidden_sizenum_hidden_layersnum_attention_heads hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_epsembedding_size trigram_inputuse_bottleneckintra_bottleneck_sizeuse_bottleneck_attentionkey_query_shared_bottlenecknum_feedforward_networksnormalization_typeclassifier_activationtrue_hidden_sizeclassifier_dropout)selfrrrrrrrrrrrrr rrrr r!r"r#r$r%r'kwargs __class__s u/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/mobilebert/configuration_mobilebert.pyrzMobileBertConfig.__init__ls6 =l=f=$&!2#6 $!2#6 ,H)'>$.!2,,*,%:"(@%+F((@%"4%:"   $9D !#5%0D !"4)i:wr-relugg?r-g{Gz?g-q=rTTr2FTr/no_normTN)__name__ __module__ __qualname____doc__ model_typer __classcell__)r*s@r+r r sbKZJ%( #!!&$(!"$"18585r,r c6eZdZedeeeeefffdZy)MobileBertOnnxConfigreturnc`|jdk(rdddd}nddd}td|fd|fd |fgS) Nzmultiple-choicebatchchoicesequence)rr1)rrA input_idsattention_masktoken_type_ids)taskr)r( dynamic_axiss r+inputszMobileBertOnnxConfig.inputssO 99) )&8 CL&:6Ll+!<0!<0   r,N)r4r5r6propertyrstrintrGrr,r+r;r;s.   WS#X%6 67    r,r;N)r7 collectionsrtypingrconfiguration_utilsronnxrutilsr get_loggerr4loggerr r;__all__rr,r+rSsV%#3   H %H5'H5X  :  5 6r,