qiBdZddlmZddlmZej eZGddeZGddeZ Gdd eZ gd Z y ) zGroupViT model configuration)PreTrainedConfig)loggingcJeZdZdZdZdZ dfd ZxZS)GroupViTTextConfiga> 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 t|di|| |_||_||_||_||_||_| |_||_ ||_ ||_ ||_ ||_ | |_| |_| |_y)N)super__init__ pad_token_id bos_token_id eos_token_id vocab_size hidden_sizeintermediate_sizedropoutnum_hidden_layersnum_attention_headsmax_position_embeddingslayer_norm_eps hidden_actinitializer_rangeinitializer_factorattention_dropout)selfrrrrrrrrrrrrr rrkwargs __class__s e/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/groupvit/configuration_groupvit.pyr zGroupViTTextConfig.__init__Ps& "6"((($&!2 !2#6 '>$,$!2"4!2)ii M quick_geluh㈵>r'{Gz??ii__name__ __module__ __qualname____doc__ model_typebase_config_keyr __classcell__rs@rrrsN3 j'J#O "!#3#3r rc`eZdZdZdZdZddgddgdgd d d d d dddddddddgffd ZxZS)GroupViTVisionConfiga@ 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)rrr")@)r9r:r:r8rgelur&r'r(r)g?r#c t|di|||_||_||_|t |k7r$t jd|dt |||_||_ ||_ ||_ ||_ | |_ | |_| |_| |_| |_||_||_||_||_||_y)Nz&Manually setting num_hidden_layers to z1, but we expect num_hidden_layers = sum(depth) = r )r r rrdepthssumloggerwarningrnum_group_tokensnum_output_groupsr image_size patch_size num_channelsrrrrrr assign_epsassign_mlp_ratio)rrrr@rrDrErrFrGrHrrrrrrrIrJrrs rr zGroupViTVisionConfig.__init__s, "6"&!2 F + NN89J8KL!!$V / "3 0!2#6 $$($, !2!2"4$ 0r r+r3s@rr5r5vs[5 n)J%O#$q'.1.1r r5c<eZdZdZdZeedZ dfd ZxZ S)GroupViTConfiga [`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. groupvit)rr7c ^|jdd}|jdd}||i}tdi|j} | jD]B\} } | |vs | || k7s| dk7s| |vr d| d| d} nd| d} tj | D|j | ||i}tdi|j} d | vr3| d jD cic]\} } t| | c} } | d <| jD]B\} } | |vs | || k7s| dk7s| |vr d| d | d} nd | d} tj | D|j | | t}tj d nt|tr tdi|}| t}tj d nt|tr tdi|}||_ ||_ ||_ ||_||_d|_d|_d|_t'|Pdi|ycc} } w)Ntext_config_dictvision_config_dicttransformers_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.r(r)Fr )poprto_dictitemsrBinfoupdater5str isinstancedictrr7projection_dimprojection_intermediate_dimlogit_scale_init_valuerroutput_segmentationr r )rrr7r\r]r^rrOrP_text_config_dictkeyvaluemessage_vision_config_dictrs rr zGroupViTConfig.__init__s"::&8$?#ZZ(UW KK( )"  !4 5  ,.K KKm n  T *,;{;K  02M KKq r  t ,0A=AM&*,+F(&<#!%"%#(  "6"[3s$H))NNr!ig/L F@) r,r-r.r/r0rr5 sub_configsr r2r3s@rrLrLs72J"4G[\K$(% b#b#r rL)rLrr5N) r/configuration_utilsrutilsr get_loggerr,rBrr5rL__all__r r rrjs\#3   H %\3)\3~i1+i1X#%#D Kr