fThJSrSSKJr SSKJrJrJrJr SSKJ r SSK J r SSK J r \(a SSKJr SS K Jr \ R""\5r"S S \ 5r"S S \ 5r"SS\ 5r"SS\ 5r/SQrg)zGroupViT model configuration OrderedDict) TYPE_CHECKINGAnyMappingOptional)PretrainedConfig) OnnxConfig)logging)ProcessorMixin) TensorTypecV^\rSrSrSrSrSrSU4SjjrSrU=r $)GroupViTTextConfig!a This is the configuration class to store the configuration of a [`GroupViTTextModel`]. It is used to instantiate an GroupViT model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the GroupViT [nvidia/groupvit-gcc-yfcc](https://huggingface.co/nvidia/groupvit-gcc-yfcc) 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 GroupViT text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`GroupViTModel`]. hidden_size (`int`, *optional*, defaults to 256): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 1024): 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 4): Number of attention heads for each attention layer in the Transformer encoder. max_position_embeddings (`int`, *optional*, defaults to 77): 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-5): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. dropout (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. 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 GroupViTTextConfig, GroupViTTextModel >>> # Initializing a GroupViTTextModel with nvidia/groupvit-gcc-yfcc style configuration >>> configuration = GroupViTTextConfig() >>> model = GroupViTTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```groupvit_text_model text_configc >[TU]"SXUS.UD6 XlX lX0lXlX@lXPlX`lXl Xpl Xl Xl Xl g)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_size hidden_sizeintermediate_sizedropoutnum_hidden_layersnum_attention_headsmax_position_embeddingslayer_norm_eps hidden_actinitializer_rangeinitializer_factorattention_dropout)selfrrrrr r!r#r"rr&r$r%rrrkwargs __class__s k/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/groupvit/configuration_groupvit.pyrGroupViTTextConfig.__init__Zsc& sl\hslrs$&!2 !2#6 '>$,$!2"4!2) r&rr#rr%r$rr"r!r rr)ii M quick_geluh㈵>r3{Gz??ii __name__ __module__ __qualname____firstlineno____doc__ model_typebase_config_keyr__static_attributes__ __classcell__r)s@r*rr!sN3 j'J#O "! 3 3r,rcl^\rSrSrSrSrSrSS/SQS/S Q/S QS S S SSSSSSSSSS/4U4SjjrSrU=r $)GroupViTVisionConfig}a This is the configuration class to store the configuration of a [`GroupViTVisionModel`]. It is used to instantiate an GroupViT model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the GroupViT [nvidia/groupvit-gcc-yfcc](https://huggingface.co/nvidia/groupvit-gcc-yfcc) 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 384): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 1536): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. depths (`List[int]`, *optional*, defaults to [6, 3, 3]): The number of layers in each encoder block. num_group_tokens (`List[int]`, *optional*, defaults to [64, 8, 0]): The number of group tokens for each stage. num_output_groups (`List[int]`, *optional*, defaults to [64, 8, 8]): The number of output groups for each stage, 0 means no group. num_attention_heads (`int`, *optional*, defaults to 6): Number of attention heads for each attention layer in the Transformer encoder. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 16): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"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-5): The epsilon used by the layer normalization layers. dropout (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. 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 GroupViTVisionConfig, GroupViTVisionModel >>> # Initializing a GroupViTVisionModel with nvidia/groupvit-gcc-yfcc style configuration >>> configuration = GroupViTVisionConfig() >>> model = GroupViTVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```groupvit_vision_model vision_configii)r r r.)@r)rHrIrIrGr gelur2r3r4r5g?r/c j>[TU]"S0UD6 XlX lX0lU[ U5:wa$[ RSUS[ U535 X@lXPl X`l Xpl Xl Xl XlXlXlXlXlXlUUlUUlUUlg)Nz&Manually setting num_hidden_layers to z1, but we expect num_hidden_layers = sum(depth) = r)rrrrdepthssumloggerwarningrnum_group_tokensnum_output_groupsr image_size patch_size num_channelsr#r"rr&r$r% assign_epsassign_mlp_ratio)r'rrrNrrRrSr rTrUrVr#r"rr&r$r%rWrXr(r)s r*rGroupViTVisionConfig.__init__s, "6"&!2 F + NN89J8KL!!$V / "3 0!2#6 $$($, !2!2"4$ 0r,)rWrXr&rNrr#rrTr%r$rr"r rVrRrrSrUr7rAs@r*rCrC}s[5 n)J%O#$q'.1.1r,rCcd^\rSrSrSrSr\\S.rS U4Sjjr \ S\S\4Sj5r S r U=r $) GroupViTConfigat [`GroupViTConfig`] is the configuration class to store the configuration of a [`GroupViTModel`]. It is used to instantiate a GroupViT 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 GroupViT [nvidia/groupvit-gcc-yfcc](https://huggingface.co/nvidia/groupvit-gcc-yfcc) 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 [`GroupViTTextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`GroupViTVisionConfig`]. projection_dim (`int`, *optional*, defaults to 256): Dimensionality of text and vision projection layers. projection_intermediate_dim (`int`, *optional*, defaults to 4096): Dimensionality of intermediate layer 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 GroupViT implementation. kwargs (*optional*): Dictionary of keyword arguments. groupvitrrFc >URSS5nURSS5n[TU]"S0UD6 UbUc0n[S0UD6R 5n U R 5HHupX;dM XU :wdMU S;dMX;a SU SU S3n OSU S3n [ RU 5 MJ URU 5 UbUc0n[S0UD6R 5n S U ;a5U S R 5V V s0sHup[U 5U _M sn n U S 'U R 5HHupX;dM XU :wdMU S;dMX;a SU S U S3n OS U S3n [ RU 5 MJ URU 5 Uc0n[ RS 5 Uc0n[ RS 5 [S0UD6Ul [S0UD6Ul X0l X@lXPlSUlSUlSUlgs sn n f)Ntext_config_dictvision_config_dict)transformers_version`zp` is found in both `text_config_dict` and `text_config` but with different values. The value `text_config_dict["z"]` will be used instead.zn`text_config_dict` is provided which will be used to initialize `GroupViTTextConfig`. The value `text_config["z"]` will be overridden.id2labelzv` is found in both `vision_config_dict` and `vision_config` but with different values. The value `vision_config_dict["zt`vision_config_dict` is provided which will be used to initialize `GroupViTVisionConfig`. The value `vision_config["zS`text_config` is `None`. Initializing the `GroupViTTextConfig` with default values.zW`vision_config` is `None`. initializing the `GroupViTVisionConfig` with default values.r4r5Fr)poprrrto_dictitemsrPinfoupdaterCstrrrFprojection_dimprojection_intermediate_dimlogit_scale_init_valuer$r%output_segmentation)r'rrFrkrlrmr(r`ra_text_config_dictkeyvaluemessage_vision_config_dictr)s r*rGroupViTConfig.__init__si"::&8$?#ZZ(UW KK(:"  !4 5  K KKm n  M KKq r-< <1BMB,+F(&<#!%"%#( Q3sH rrFc PU"SUR5UR5S.UD6$)z Instantiate a [`GroupViTConfig`] (or a derived class) from groupvit text model configuration and groupvit vision model configuration. Returns: [`GroupViTConfig`]: An instance of a configuration object r^r)rf)clsrrFr(s r*from_text_vision_configs'GroupViTConfig.from_text_vision_configsgs,f{224MDYDYD[f_effr,)r%r$rmrnrkrlrrF)NNr-ig/L F@)r8r9r:r;r<r=rrC sub_configsr classmethodrwr?r@rAs@r*r[r[sZ2J"4G[\K$(% _)B g3E gVj g gr,r[c ^\rSrSr\S\\\\\444Sj5r\S\\\\\444Sj5r \S\ 4Sj5r SSSS\S \S \ S S\\\ 44 U4S jjjr\S\4S j5rSrU=r$)GroupViTOnnxConfigitreturnc @[SSSS.4SSSSSS .4S SSS.4/5$) N input_idsbatchsequence)rr6 pixel_valuesrVheightwidth)rr6r attention_maskrr's r*inputsGroupViTOnnxConfig.inputsus@'j9:WHQX!YZ!w:#>?   r,c@[SSS04SSS04SSS04SSS04/5$)Nlogits_per_imagerrlogits_per_text text_embeds image_embedsrrs r*outputsGroupViTOnnxConfig.outputssD#a\2"QL1G -!W.    r,cg)Ng-C6?rrs r*atol_for_validation&GroupViTOnnxConfig.atol_for_validationsr, processorr batch_size seq_length frameworkrcr>[TU]URX#US9n[TU]URX$S9n0UEUE$)N)rrr)rr)rgenerate_dummy_inputs tokenizerimage_processor)r'rrrrtext_input_dictimage_input_dictr)s r*r(GroupViTOnnxConfig.generate_dummy_inputss\ '7   JYb8 !78  % %*9 7/6%566r,cg)Nrrs r*default_onnx_opset%GroupViTOnnxConfig.default_onnx_opsetsr,r)rN)r8r9r:r;propertyrrjintrrfloatrrrrrr?r@rAs@r*r|r|ts  WS#X%6 67   gc3h&7!78  U ,0 7# 7 7 7 L) 7 c  7 7Cr,r|)r[r|rrCN)r< collectionsrtypingrrrrconfiguration_utilsr onnxr utilsr processing_utilsr r get_loggerr8rPrrCr[r|__all__rr,r*rs##8832#   H %Y3)Y3xi1+i1XHg%HgV++\ ar,