§ ‚Štj?ãó„—dZddlmZddlmZddlmZed¬¦«eGd„d e¦«¦«¦«Zd gZd S) zLXMERT model configurationé)Ústricté)ÚPreTrainedConfig)Úauto_docstringzunc-nlp/lxmert-base-uncased)Ú checkpointcó‡—eZdZUdZdZiZdZeed<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<ˆfd4„Z*ˆxZ+S)5Ú LxmertConfigaá 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 Úlxmerti:wÚ vocab_sizeiÚ hidden_sizeé Únum_attention_headsi%Ú num_qa_labelsi@Únum_object_labelsiÚnum_attr_labelsi Úintermediate_sizeÚgeluÚ hidden_actgš™™™™™¹?Úhidden_dropout_probÚattention_probs_dropout_probiÚmax_position_embeddingséÚtype_vocab_sizeg{®Gáz”?Úinitializer_rangeé Úl_layerséÚx_layersÚr_layersiÚvisual_feat_diméÚvisual_pos_dimg®Gáz®@Úvisual_loss_normalizerTÚ task_matchedÚ task_mask_lmÚtask_obj_predictÚtask_qaÚvisual_obj_lossÚvisual_attr_lossÚvisual_feat_lossNÚ pad_token_idÚ bos_token_idÚ eos_token_idÚtie_word_embeddingsc ón•—|j|j|jdœ|_t ¦«jdi|¤ŽdS)N)ÚvisionÚ cross_encoderÚlanguage©)rrrÚnum_hidden_layersÚsuperÚ __post_init__)ÚselfÚkwargsÚ __class__s €úm/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/lxmert/configuration_lxmert.pyr6zLxmertConfig.__post_init__gs@ø€Ø,0¬MÈDÌMÐgkÔgtÐ!uÐ!uˆÔ؉ŒÔÐ'Ð' Ð'Ð'Ð'Ð'Ð'ó),Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚ attribute_mapr ÚintÚ__annotations__r rrrrrrÚstrrÚfloatrrrrrrrr r"r#r$Úboolr%r&r'r(r)r*r+r,r-Úlistr.r6Ú __classcell__)r9s@r:r r sZø€€€€€€ð*ð*ðX€JØ€Mà€JÐÐÑØ€KÐÐÑØ!ИÐ!Ð!Ñ!Ø€M3ÐÐÑØ!ÐsÐ!Ð!Ñ!Ø€OSÐÐÑØ!ÐsÐ!Ð!Ñ!Ø€JÐÐÑØ'*И ™Ð*Ð*Ñ*Ø03Ð  %¨#¡+Ð3Ð3Ñ3Ø#&ИSÐ&Ð&Ñ&Ø€OSÐÐÑØ#ÐuÐ#Ð#Ñ#Ø€HˆcÐÐÑØ€HˆcÐÐÑØ€HˆcÐÐÑØ€OSÐÐÑØ€NCÐÐÑØ$(ИEÐ(Ð(Ñ(Ø€L$ÐÐÑØ€L$ÐÐÑØ!ÐdÐ!Ð!Ñ!Ø€GˆTÐÐÑØ €OTÐ Ð Ñ Ø!ÐdÐ!Ð!Ñ!Ø!ÐdÐ!Ð!Ñ!Ø#€L#˜‘*Ð#Ð#Ñ#Ø#€L#˜‘*Ð#Ð#Ñ#Ø+/€L#˜˜Sœ ‘/ DÑ(Ð/Ð/Ñ/Ø $ИÐ$Ð$Ñ$ð(ð(ð(ð(ð(ð(ð(ð(ð(r;r N) r?Úhuggingface_hub.dataclassesrÚconfiguration_utilsrÚutilsrr Ú__all__r3r;r:úrMsªðð!Ð à.Ð.Ð.Ð.Ð.Ð.à3Ð3Ð3Ð3Ð3Ð3Ø#Ð#Ð#Ð#Ð#Ð#ð€Ð8Ð9Ñ9Ô9ØðQ(ðQ(ðQ(ðQ(ðQ(Ð#ñQ(ôQ(ñ„ñ:Ô9ðQ(ðh Ð €€€r;