^jRdZddlmZddlmZddlmZmZeje Z edeGdd eZ edeGd d eZ edeGd d eZ gdZy)zBlip model configuration)strict)PreTrainedConfig)auto_docstringloggingzSalesforce/blip-vqa-base) checkpointcpeZdZUdZdZdZdZeed<dZ eed<dZ eed<d Z eed <dZ eed <d Z eed <dZeed<dZeed<dZeed<dZeed<dZeezed<dZeezed<dZeed<dZedzed<dZeeezdzed<d Zedzed!<d"Zedzed#<d$Zeed%<d$Zeed&<d$Zeed'<dZ eed(<y))BlipTextConfigaq label_smoothing (float, *optional*): A float in [0.0, 1.0]. Specifies the amount of smoothing when computing the loss, where 0.0 means no smoothing. The targets become a mixture of the original ground truth and a uniform distribution as described in `Rethinking the Inception Architecture for Computer Vision `__. Default: :math:`0.0`. Example: ```python >>> from transformers import BlipTextConfig, BlipTextModel >>> # Initializing a BlipTextConfig with Salesforce/blip-vqa-base style configuration >>> configuration = BlipTextConfig() >>> # Initializing a BlipTextModel (with random weights) from the Salesforce/blip-vqa-base style configuration >>> model = BlipTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```blip_text_model text_configi>> from transformers import BlipVisionConfig, BlipVisionModel >>> # Initializing a BlipVisionConfig with Salesforce/blip-vqa-base style configuration >>> configuration = BlipVisionConfig() >>> # Initializing a BlipVisionModel (with random weights) from the Salesforce/blip-vqa-base style configuration >>> model = BlipVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```blip_vision_model vision_configrrrrrrrrri image_size patch_sizerrgh㈵>rrattention_dropoutg|=r!N)r,r-r.r/r0r1rr2r3rrrrr?r6tuplerArr4rr5rBr!r8r9r:r<r<Ks %J%OK!s!NCs!!47Jd3i%S/1746Jd3i%S/16J NE %(us{($u$r9r<ceZdZUdZdZeedZdZe e zdze d<dZ e e zdze d<dZ ee d<d Zee d <d Zee d <d Zee d<dZee d<dZee d<dZee d<fdZxZS) BlipConfiga' image_text_hidden_size (`int`, *optional*, defaults to 256): Dimensionality of the hidden state of the image-text fusion layer. label_smoothing (float, *optional*): A float in [0.0, 1.0]. Specifies the amount of smoothing when computing the loss, where 0.0 means no smoothing. The targets become a mixture of the original ground truth and a uniform distribution as described in `Rethinking the Inception Architecture for Computer Vision `__. Default: :math:`0.0`. Example: ```python >>> from transformers import BlipConfig, BlipModel >>> # Initializing a BlipConfig with Salesforce/blip-vqa-base style configuration >>> configuration = BlipConfig() >>> # Initializing a BlipPModel (with random weights) from the Salesforce/blip-vqa-base style configuration >>> model = BlipModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a BlipConfig from a BlipTextConfig and a BlipVisionConfig >>> # Initializing a BLIPText and BLIPVision configuration >>> config_text = BlipTextConfig() >>> config_vision = BlipVisionConfig() >>> config = BlipConfig(text_config=config_text, vision_config=config_vision) ```blip)r r>Nr r>rrg/L F@logit_scale_init_valueimage_text_hidden_sizerr+Tr*g?initializer_factorr r!c |j%t|_tjdn4t |jt rtdi|j|_|j %t|_tjdn4t |j t rtdi|j |_|j j|j_ t|,di|y)NzO`text_config` is `None`. Initializing the `BlipTextConfig` with default values.zS`vision_config` is `None`. initializing the `BlipVisionConfig` with default values.r8) r r loggerinfo isinstancedictr>r<rrsuper __post_init__)selfkwargs __class__s r:rQzBlipConfig.__post_init__s    #-/D  KKi j (($ /-A0@0@AD     %!1!3D  KKm n **D 1!1!GD4F4F!GD /3/A/A/M/M, ''r9)r,r-r.r/r0r r< sub_configsr rOrr3r>rr2rGr5rIr+r*r7rJr!rQ __classcell__)rTs@r:rErEns >J"0CSTK26K((4/648M4**T18NC$*E*"%C% OU $$ ###u#((r9rE)rEr r<N)r/huggingface_hub.dataclassesrconfiguration_utilsrutilsrr get_loggerr,rLr r<rE__all__r8r9r:r\s.3,   H %56-!%-!7-!`56%'%7%B56<(!<(7<(~ ?r9