o ߥi@s8dZddlmZddlmZeZGdddeZdS)zV StructBERT model configuration, mainly copied from :class:`~transformers.BertConfig` )PretrainedConfig)loggercsFeZdZdZdZ           dfdd ZZS) SbertConfiga This is the configuration class to store the configuration of a :class:`~modelscope.models.nlp.structbert.SbertModel`. It is used to instantiate a StructBERT model according to the specified arguments. Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information. Args: vocab_size (:obj:`int`, `optional`, defaults to 30522): Vocabulary size of the BERT model. Defines the number of different tokens that can be represented by the :obj:`inputs_ids` passed when calling :class:`~transformers.BertModel` or :class:`~transformers.TFBertModel`. hidden_size (:obj:`int`, `optional`, defaults to 768): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (:obj:`int`, `optional`, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (:obj:`int`, `optional`, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (:obj:`int`, `optional`, defaults to 3072): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. hidden_act (:obj:`str` or :obj:`Callable`, `optional`, defaults to :obj:`"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, :obj:`"gelu"`, :obj:`"relu"`, :obj:`"silu"` and :obj:`"gelu_new"` are supported. hidden_dropout_prob (:obj:`float`, `optional`, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (:obj:`float`, `optional`, defaults to 0.1): The dropout ratio for the attention probabilities. max_position_embeddings (:obj:`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 (:obj:`int`, `optional`, defaults to 2): The vocabulary size of the :obj:`token_type_ids` passed when calling :class:`~transformers.BertModel` or :class:`~transformers.TFBertModel`. initializer_range (:obj:`float`, `optional`, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (:obj:`float`, `optional`, defaults to 1e-12): The epsilon used by the layer normalization layers. position_embedding_type (:obj:`str`, `optional`, defaults to :obj:`"absolute"`): Type of position embedding. Choose one of :obj:`"absolute"`, :obj:`"relative_key"`, :obj:`"relative_key_query"`. For positional embeddings use :obj:`"absolute"`. For more information on :obj:`"relative_key"`, please refer to `Self-Attention with Relative Position Representations (Shaw et al.) `__. For more information on :obj:`"relative_key_query"`, please refer to `Method 4` in `Improve Transformer Models with Better Relative Position Embeddings (Huang et al.) `__. use_cache (:obj:`bool`, `optional`, defaults to :obj:`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 (:obj:`float`, `optional`): The dropout ratio for the classification head. adv_grad_factor (:obj:`float`, `optional`): This factor will be multiplied by the KL loss grad and then the result will be added to the original embedding. More details please check:https://arxiv.org/abs/1908.04577 The range of this value should between 1e-3~1e-7 adv_bound (:obj:`float`, `optional`): adv_bound is used to cut the top and the bottom bound of the produced embedding. If not provided, 2 * sigma will be used as the adv_bound factor sigma (:obj:`float`, `optional`): The std factor used to produce a 0 mean normal distribution. If adv_bound not provided, 2 * sigma will be used as the adv_bound factor structbert:w gelu皙?{Gz?-q=rabsoluteTNc stjdd| i|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_||_d|vr>dn|d|_d|vrIdn|d|_d|vrZd|j|_dS|d|_dS) N pad_token_idadv_grad_factorg-C6 ?sigmagh㈵> adv_boundr )super__init__ vocab_size hidden_sizenum_hidden_layersnum_attention_heads hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_epsposition_embedding_type use_cacheclassifier_dropoutrrr)selfrrrrrrrrr r!r"r#rr$r%r&kwargs __class__rb/home/ubuntu/.local/lib/python3.10/site-packages/modelscope/models/nlp/structbert/configuration.pyrZs. zSbertConfig.__init__)rrrrr r r r r r rrrrTN)__name__ __module__ __qualname____doc__ model_typer __classcell__rrr)r+rs(>rN)r/ transformersrmodelscope.utilsrlogging get_loggerrrrrr+s