fThN8SrSSKJr SSKJrJrJrJrJr \(a SSK J r SSK J r SSK Jr SSKJr SS K Jr \R$"\5r"S S \5r"S S \5r"SS\5r"SS\5r/SQrg)zOWL-ViT model configuration OrderedDict) TYPE_CHECKINGAnyDictMappingOptional)ProcessorMixin) TensorType)PretrainedConfig) OnnxConfig)loggingcT^\rSrSrSrSrSrSU4SjjrSrU=r $)OwlViTTextConfig!a This is the configuration class to store the configuration of an [`OwlViTTextModel`]. It is used to instantiate an OwlViT text encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the OwlViT [google/owlvit-base-patch32](https://huggingface.co/google/owlvit-base-patch32) 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 49408): Vocabulary size of the OWL-ViT text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`OwlViTTextModel`]. hidden_size (`int`, *optional*, defaults to 512): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 2048): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer encoder. max_position_embeddings (`int`, *optional*, defaults to 16): 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). hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). pad_token_id (`int`, *optional*, defaults to 0): The id of the padding token in the input sequences. bos_token_id (`int`, *optional*, defaults to 49406): The id of the beginning-of-sequence token in the input sequences. eos_token_id (`int`, *optional*, defaults to 49407): The id of the end-of-sequence token in the input sequences. Example: ```python >>> from transformers import OwlViTTextConfig, OwlViTTextModel >>> # Initializing a OwlViTTextModel with google/owlvit-base-patch32 style configuration >>> configuration = OwlViTTextConfig() >>> # Initializing a OwlViTTextConfig from the google/owlvit-base-patch32 style configuration >>> model = OwlViTTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```owlvit_text_model text_configc >[TU]"SXUS.UD6 XlX lX0lX@lXPlX`lXplXl Xl Xl Xl g)N) pad_token_id bos_token_id eos_token_id) super__init__ vocab_size hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsmax_position_embeddings hidden_actlayer_norm_epsattention_dropoutinitializer_rangeinitializer_factor)selfrrrrr r!r"r#r$r%r&rrrkwargs __class__s g/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/owlvit/configuration_owlvit.pyrOwlViTTextConfig.__init__`s^$ sl\hslrs$&!2!2#6 '>$$,!2!2"4) r$r"rr&r%rr#r!r rr)ii  quick_geluh㈵>{Gz??rii __name__ __module__ __qualname____firstlineno____doc__ model_typebase_config_keyr__static_attributes__ __classcell__r)s@r*rr!sK9 v%J#O "55r,rcP^\rSrSrSrSrSrSU4SjjrSrU=r $)OwlViTVisionConfiga This is the configuration class to store the configuration of an [`OwlViTVisionModel`]. It is used to instantiate an OWL-ViT image encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the OWL-ViT [google/owlvit-base-patch32](https://huggingface.co/google/owlvit-base-patch32) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. 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. num_channels (`int`, *optional*, defaults to 3): Number of channels in the input images. image_size (`int`, *optional*, defaults to 768): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 32): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). Example: ```python >>> from transformers import OwlViTVisionConfig, OwlViTVisionModel >>> # Initializing a OwlViTVisionModel with google/owlvit-base-patch32 style configuration >>> configuration = OwlViTVisionConfig() >>> # Initializing a OwlViTVisionModel model from the google/owlvit-base-patch32 style configuration >>> model = OwlViTVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```owlvit_vision_model vision_configc  >[TU]"S0U D6 XlX lX0lX@lXPlX`lXplXl Xl Xl Xl Xl g)Nr)rrrrrr num_channels image_size patch_sizer"r#r$r%r&)r'rrrr rGrHrIr"r#r$r%r&r(r)s r*rOwlViTVisionConfig.__init__sZ "6"&!2!2#6 ($$$,!2!2"4r,) r$r"rrHr&r%rr#r rGrrI) i r.r.r rK r1r2r3r4r5r6r@s@r*rBrBsE2 h'J%O55r,rBcd^\rSrSrSrSr\\S.rS U4Sjjr \ S\ S\ 4Sj5r S r U=r$) OwlViTConfigai [`OwlViTConfig`] is the configuration class to store the configuration of an [`OwlViTModel`]. It is used to instantiate an OWL-ViT model according to the specified arguments, defining the text model and vision model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the OWL-ViT [google/owlvit-base-patch32](https://huggingface.co/google/owlvit-base-patch32) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: text_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`OwlViTTextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`OwlViTVisionConfig`]. projection_dim (`int`, *optional*, defaults to 512): Dimensionality of text and vision projection layers. logit_scale_init_value (`float`, *optional*, defaults to 2.6592): The initial value of the *logit_scale* parameter. Default is used as per the original OWL-ViT implementation. return_dict (`bool`, *optional*, defaults to `True`): Whether or not the model should return a dictionary. If `False`, returns a tuple. kwargs (*optional*): Dictionary of keyword arguments. owlvit)rrEc >[TU]"S0UD6 Uc0n[RS5 Uc0n[RS5 [ S0UD6Ul[ S0UD6UlX0lX@l XPl SUl g)NzKtext_config is None. Initializing the OwlViTTextConfig with default values.zOvision_config is None. initializing the OwlViTVisionConfig with default values.r5r) rrloggerinforrrBrEprojection_dimlogit_scale_init_value return_dictr&)r'rrErTrUrVr(r)s r*rOwlViTConfig.__init__s "6"  K KKe f  M KKi j+:k:/@-@,&<#&"%r,rrEc <0nXS'X$S'UR"U40UD6$)z Instantiate a [`OwlViTConfig`] (or a derived class) from owlvit text model configuration and owlvit vision model configuration. Returns: [`OwlViTConfig`]: An instance of a configuration object rrE) from_dict)clsrrEr( config_dicts r*from_text_vision_configs%OwlViTConfig.from_text_vision_configss- %0M"'4O$}}[3F33r,)r&rUrTrVrrE)NNr-g/L F@T)r7r8r9r:r;r<rrB sub_configsr classmethodrr\r>r?r@s@r*rNrNsR2J"2EWXK% &6 44 4 4 4r,rNc ^\rSrSr\S\\\\\444Sj5r\S\\\\\444Sj5r \S\ 4Sj5r SSSS\S \S \ S S\\\ 44 U4S jjjr\S\4S j5rSrU=r$)OwlViTOnnxConfigi!returnc @[SSSS.4SSSSSS .4S SSS.4/5$) N input_idsbatchsequence)r pixel_valuesrGheightwidth)rrgr attention_maskrr's r*inputsOwlViTOnnxConfig.inputs"s@'j9:WHQX!YZ!w:#>?   r,c@[SSS04SSS04SSS04SSS04/5$)Nlogits_per_imagerrelogits_per_text text_embeds image_embedsrrms r*outputsOwlViTOnnxConfig.outputs,sD#a\2"QL1G -!W.    r,cg)Ng-C6?rrms r*atol_for_validation$OwlViTOnnxConfig.atol_for_validation7sr, processorr batch_size seq_length frameworkr cr>[TU]URX#US9n[TU]URX$S9n0UEUE$)N)r{r|r})r{r})rgenerate_dummy_inputs tokenizerimage_processor)r'rzr{r|r}text_input_dictimage_input_dictr)s r*r&OwlViTOnnxConfig.generate_dummy_inputs;s\ '7   JYb8 !78  % %*9 7/6%566r,cg)Nrrms r*default_onnx_opset#OwlViTOnnxConfig.default_onnx_opsetJsr,r)rN)r7r8r9r:propertyrstrintrnrufloatrxr rrrr>r?r@s@r*rara!s  WS#X%6 67   gc3h&7!78  U ,0 7# 7 7 7 L) 7 c  7 7Cr,ra)rNrarrBN)r; collectionsrtypingrrrrr processing_utilsr utilsr configuration_utilsr onnxrr get_loggerr7rRrrBrNra__all__rr,r*rs~"#>>2#3   H %]5']5@U5)U5pE4#E4P+z+\ Yr,