g^dZddlmZddlmZejeZGddeZdS)zLUKE configuration)PretrainedConfig)loggingcNeZdZdZdZ dfd ZxZS) LukeConfiga( This is the configuration class to store the configuration of a [`LukeModel`]. It is used to instantiate a LUKE 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 LUKE [studio-ousia/luke-base](https://huggingface.co/studio-ousia/luke-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 50267): Vocabulary size of the LUKE model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`LukeModel`]. entity_vocab_size (`int`, *optional*, defaults to 500000): Entity vocabulary size of the LUKE model. Defines the number of different entities that can be represented by the `entity_ids` passed when calling [`LukeModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. entity_emb_size (`int`, *optional*, defaults to 256): The number of dimensions of the entity embedding. 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 [`LukeModel`]. 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. use_entity_aware_attention (`bool`, *optional*, defaults to `True`): Whether or not the model should use the entity-aware self-attention mechanism proposed in [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention (Yamada et al.)](https://arxiv.org/abs/2010.01057). classifier_dropout (`float`, *optional*): The dropout ratio for the classification head. pad_token_id (`int`, *optional*, defaults to 1): Padding token id. bos_token_id (`int`, *optional*, defaults to 0): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 2): End of stream token id. Examples: ```python >>> from transformers import LukeConfig, LukeModel >>> # Initializing a LUKE configuration >>> configuration = LukeConfig() >>> # Initializing a model from the configuration >>> model = LukeModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```luke[  gelu皙?{Gz?-q=TNc "tjd|||d|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_dS)zConstructs LukeConfig.) pad_token_id bos_token_id eos_token_idN)super__init__ vocab_sizeentity_vocab_size hidden_sizeentity_emb_sizenum_hidden_layersnum_attention_heads hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_epsuse_entity_aware_attentionclassifier_dropout)selfrrrr r!r"r$r#r%r&r'r(r)r*r+r,rrrkwargs __class__s g/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/luke/configuration_luke.pyrzLukeConfig.__init__bs0 sl\hsslrsss$!2&.!2#6 $!2#6 ,H)'>$.!2,*D'"4)rr r r r r r rrrrrrrTNrrr)__name__ __module__ __qualname____doc__ model_typer __classcell__)r/s@r0rrsE E NJ %( ##'))5)5)5)5)5)5)5)5)5)5r1rN) r5configuration_utilsrutilsr get_loggerr2loggerrrr1r0r<s333333  H % %s5s5s5s5s5!s5s5s5s5s5r1