from transformers.configuration_utils import PretrainedConfig class UbkeConfig(PretrainedConfig): model_type = "ubke" def __init__( self, vocab_size=50267, entity_vocab_size=500000, num_category_entities=0, hidden_size=768, entity_emb_size=256, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072, hidden_act="gelu", hidden_dropout_prob=0.1, attention_probs_dropout_prob=0.1, max_position_embeddings=512, type_vocab_size=2, initializer_range=0.02, layer_norm_eps=1e-12, use_entity_aware_attention=True, classifier_dropout=None, normalize_entity_embeddings=False, entity_temperature=1.0, pad_token_id=1, bos_token_id=0, eos_token_id=2, **kwargs, ): super().__init__( pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs, ) self.vocab_size = vocab_size self.entity_vocab_size = entity_vocab_size self.num_category_entities = num_category_entities self.hidden_size = hidden_size self.entity_emb_size = entity_emb_size self.num_hidden_layers = num_hidden_layers self.num_attention_heads = num_attention_heads self.hidden_act = hidden_act self.intermediate_size = intermediate_size self.hidden_dropout_prob = hidden_dropout_prob self.attention_probs_dropout_prob = attention_probs_dropout_prob self.max_position_embeddings = max_position_embeddings self.type_vocab_size = type_vocab_size self.initializer_range = initializer_range self.layer_norm_eps = layer_norm_eps self.use_entity_aware_attention = use_entity_aware_attention self.classifier_dropout = classifier_dropout self.normalize_entity_embeddings = normalize_entity_embeddings self.entity_temperature = entity_temperature