U 4Af@sndZddlmZddlmZddlmZddlmZddl m Z e e Z Gdd d eZGd d d eZd S) zERNIE model configuration) OrderedDict)Mapping)PretrainedConfig) OnnxConfig)loggingcs&eZdZdZdZdfdd ZZS) ErnieConfiga This is the configuration class to store the configuration of a [`ErnieModel`] or a [`TFErnieModel`]. It is used to instantiate a ERNIE 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 ERNIE [nghuyong/ernie-3.0-base-zh](https://huggingface.co/nghuyong/ernie-3.0-base-zh) 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 ERNIE model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`ErnieModel`] or [`TFErnieModel`]. 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). type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the `token_type_ids` passed when calling [`ErnieModel`] or [`TFErnieModel`]. task_type_vocab_size (`int`, *optional*, defaults to 3): The vocabulary size of the `task_type_ids` for ERNIE2.0/ERNIE3.0 model use_task_id (`bool`, *optional*, defaults to `False`): Whether or not the model support `task_type_ids` 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): Padding token id. position_embedding_type (`str`, *optional*, defaults to `"absolute"`): Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155). For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658). use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. classifier_dropout (`float`, *optional*): The dropout ratio for the classification head. Examples: ```python >>> from transformers import ErnieConfig, ErnieModel >>> # Initializing a ERNIE nghuyong/ernie-3.0-base-zh style configuration >>> configuration = ErnieConfig() >>> # Initializing a model (with random weights) from the nghuyong/ernie-3.0-base-zh style configuration >>> model = ErnieModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zernie:w gelu皙?rF{Gz?-q=rabsoluteTNc stjfd|i|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_||_dS)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_sizetask_type_vocab_size use_task_idinitializer_rangelayer_norm_epsposition_embedding_type use_cacheclassifier_dropout)selfrrrrrrrrrr r!r"r#r$rr%r&r'kwargs __class__Q/tmp/pip-unpacked-wheel-zw5xktn0/transformers/models/ernie/configuration_ernie.pyrgs$zErnieConfig.__init__)r r r r r r rrrrrFrrrrTN)__name__ __module__ __qualname____doc__Z model_typer __classcell__r,r,r*r-rs*Grc@s.eZdZeeeeeeffdddZdS)ErnieOnnxConfig)returncCsB|jdkrdddd}n ddd}td|fd|fd |fd |fgS) Nzmultiple-choicebatchchoicesequence)rr)rr8Z input_idsZattention_maskZtoken_type_idsZ task_type_ids)Ztaskr)r(Z dynamic_axisr,r,r-inputss  zErnieOnnxConfig.inputsN)r.r/r0propertyrstrintr9r,r,r,r-r3sr3N)r1 collectionsrtypingrZconfiguration_utilsrZonnxrutilsrZ get_loggerr.loggerrr3r,r,r,r-s      u