i?jdZddlmZddlmZddlmZedeGdd eZd gZy ) zLXMERT model configuration)strict)PreTrainedConfig)auto_docstringzunc-nlp/lxmert-base-uncased) checkpointceZdZUdZdZiZdZeed<dZ eed<dZ eed<d Z eed <d Z eed <d Z eed<dZeed<dZeed<dZeezed<dZeezed<dZeed<dZeed<dZeed<dZeed<dZeed<dZeed <d!Zeed"<d#Zeed$<d%Zeed&<d'Zeed(<d'Zeed)<d'Z eed*<d'Z!eed+<d'Z"eed,<d'Z#eed-<d'Z$eed.<d/Z%ed/zed0<d/Z&ed/zed1<d/Z'ee(ezd/zed2<d'Z)eed3<fd4Z*xZ+S)5 LxmertConfiga num_qa_labels (`int`, *optional*, defaults to 9500): This represents the total number of different question answering (QA) labels there are. If using more than one dataset with QA, the user will need to account for the total number of labels that all of the datasets have in total. num_object_labels (`int`, *optional*, defaults to 1600): This represents the total number of semantically unique objects that lxmert will be able to classify a pooled-object feature as belonging too. num_attr_labels (`int`, *optional*, defaults to 400): This represents the total number of semantically unique attributes that lxmert will be able to classify a pooled-object feature as possessing. l_layers (`int`, *optional*, defaults to 9): Number of hidden layers in the Transformer language encoder. x_layers (`int`, *optional*, defaults to 5): Number of hidden layers in the Transformer cross modality encoder. r_layers (`int`, *optional*, defaults to 5): Number of hidden layers in the Transformer visual encoder. visual_feat_dim (`int`, *optional*, defaults to 2048): This represents the last dimension of the pooled-object features used as input for the model, representing the size of each object feature itself. visual_pos_dim (`int`, *optional*, defaults to 4): This represents the number of spatial features that are mixed into the visual features. The default is set to 4 because most commonly this will represent the location of a bounding box. i.e., (x, y, width, height) visual_loss_normalizer (`float`, *optional*, defaults to 6.67): This represents the scaling factor in which each visual loss is multiplied by if during pretraining, one decided to train with multiple vision-based loss objectives. task_matched (`bool`, *optional*, defaults to `True`): This task is used for sentence-image matching. If the sentence correctly describes the image the label will be 1. If the sentence does not correctly describe the image, the label will be 0. task_mask_lm (`bool`, *optional*, defaults to `True`): Whether or not to add masked language modeling (as used in pretraining models such as BERT) to the loss objective. task_obj_predict (`bool`, *optional*, defaults to `True`): Whether or not to add object prediction, attribute prediction and feature regression to the loss objective. task_qa (`bool`, *optional*, defaults to `True`): Whether or not to add the question-answering loss to the objective visual_obj_loss (`bool`, *optional*, defaults to `True`): Whether or not to calculate the object-prediction loss objective visual_attr_loss (`bool`, *optional*, defaults to `True`): Whether or not to calculate the attribute-prediction loss objective visual_feat_loss (`bool`, *optional*, defaults to `True`): Whether or not to calculate the feature-regression loss objective lxmerti:w vocab_sizei hidden_size num_attention_headsi% num_qa_labelsi@num_object_labelsinum_attr_labelsi intermediate_sizegelu hidden_actg?hidden_dropout_probattention_probs_dropout_probimax_position_embeddingstype_vocab_sizeg{Gz?initializer_range l_layersx_layersr_layersivisual_feat_dimvisual_pos_dimgGz@visual_loss_normalizerT task_matched task_mask_lmtask_obj_predicttask_qavisual_obj_lossvisual_attr_lossvisual_feat_lossN pad_token_id bos_token_id eos_token_idtie_word_embeddingsc v|j|j|jd|_t |di|y)N)vision cross_encoderlanguage)rrrnum_hidden_layerssuper __post_init__)selfkwargs __class__s /var/www/vps2.regionflexible.com/Desarrollo/venv/lib/python3.12/site-packages/transformers/models/lxmert/configuration_lxmert.pyr6zLxmertConfig.__post_init__gs1,0MMDMMgkgtgt!u ''),__name__ __module__ __qualname____doc__ model_type attribute_mapr int__annotations__r rrrrrrstrrfloatrrrrrrrr r"r#r$boolr%r&r'r(r)r*r+r,r-listr.r6 __classcell__)r9s@r:r r st*XJMJK!!M3!s!OS!s!J'**03 %#+3#&S&OS#u#HcHcHcOSNC$(E(L$L$!d!GT OT !d!!d!#L#*##L#*#+/L#S /D(/ $$((r;r N) r?huggingface_hub.dataclassesrconfiguration_utilsrutilsrr __all__r3r;r:rMsK!.3#89Q(#Q(:Q(h  r;