o eiB@sbdZddlmZddlmZeeZGdddeZGdddeZ Gdd d eZ gd Z d S) zGroupViT model configuration)PreTrainedConfig)loggingcsHeZdZdZdZdZ         dfdd ZZS)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_config M quick_geluh㈵>{Gz??c sptjdi|| |_||_||_||_||_||_| |_||_ ||_ ||_ ||_ ||_ | |_| |_| |_dS)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)selfrrrrr r!r#r"rr&r$r%rrrkwargs __class__rq/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/groupvit/configuration_groupvit.pyrPs  zGroupViTTextConfig.__init__)rrr r r r r rrrrrrrr__name__ __module__ __qualname____doc__ model_typebase_config_keyr __classcell__rrr)r+rs(5rcs^eZdZdZdZdZddgddgdgd d d d d dddddddddgffdd ZZS)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 )@)r8r9r9r7rgelurrrrg?r c stjdi|||_||_||_|t|kr%td|dt|||_||_ ||_ ||_ ||_ | |_ | |_| |_| |_| |_||_||_||_||_||_dS)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'rrr>rrBrCr rDrErFr#r"rr&r$r%rGrHr(r)rr+rs2  zGroupViTVisionConfig.__init__r,rrr)r+r4vs.7r4cs:eZdZdZdZeedZ     d fdd ZZ 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)rr6Nr/L F@c s|dd}|dd}|durT|duri}tdi|} | D]+\} } | |vrN| || krN| dkrN| |vrCd| d| d} nd| d} t| q#|| |dur|dur^i}tdi|} d | vrxd d | d D| d <| D]+\} } | |vr| || kr| dkr| |vrd| d | d} nd | d} t| q||| |durt}tdn t|t rtdi|}|durt}tdn t|t rtdi|}||_ ||_ ||_ ||_ ||_d|_d|_d|_tjdi|dS)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.id2labelcSsi|] \}}t||qSr)str).0keyvaluerrr+ 4sz+GroupViTConfig.__init__..zv` 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.rrFr)poprto_dictitemsr@infoupdater4 isinstancedictrr6projection_dimprojection_intermediate_dimlogit_scale_init_valuer$r%output_segmentationrr)r'rr6r^r_r`r(rMrN_text_config_dictrTrUmessage_vision_config_dictr)rr+rsz           zGroupViTConfig.__init__)NNrrKrL) r-r.r/r0r1rr4 sub_configsrr3rrr)r+rIs rI)rIrr4N) r0configuration_utilsrutilsr get_loggerr-r@rr4rI__all__rrrr+s   _l