`iHdZddlmZddlmZddlmZmZmZddl m Z ddl m Z ddl mZer dd lmZdd l mZejeZGd d e ZGd de ZGdde ZGdde ZgdZdS)zGroupViT model configuration OrderedDict)Mapping) TYPE_CHECKINGAnyOptional)PretrainedConfig) OnnxConfig)logging)ProcessorMixin) TensorTypecJeZdZdZdZdZ 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_config M quick_geluh㈵>{Gz??c tjd| ||d|||_||_||_| |_||_||_||_||_ ||_ | |_ | |_ | |_ dS)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)selfr(r)r*r,r-r.r0r/r+r3r1r2r"r#r$kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/groupvit/configuration_groupvit.pyr'zGroupViTTextConfig.__init__[s& sl\hsslrsss$&!2 !2#6 '>$,$!2"4!2)rrrrrrrrrrrrrrr __name__ __module__ __qualname____doc__ model_typebase_config_keyr' __classcell__r6s@r7rr"s3 3 j'J#O "! 3 3 3 3 3 3 3 3 3 3r8rc`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)r r r)@r)rGrHrHrFr gelurrrrg?rc tjdi|||_||_||_|t |kr-t d|dt |||_||_ ||_ ||_ ||_ | |_ | |_| |_| |_| |_||_||_||_||_||_dS)Nz&Manually setting num_hidden_layers to z1, but we expect num_hidden_layers = sum(depth) = r%)r&r'r)r*depthssumloggerwarningr,num_group_tokensnum_output_groupsr- image_size patch_size num_channelsr0r/r+r3r1r2 assign_epsassign_mlp_ratio)r4r)r*rMr,rQrRr-rSrTrUr0r/r+r3r1r2rVrWr5r6s r7r'zGroupViTVisionConfig.__init__s, ""6"""&!2 F + + NN/9J//!$V//   "3 0!2#6 $$($, !2!2"4$ 0r8r9rAs@r7rCrC~s5 5 n)J%Oyy#$**q'.1.1.1.1.1.1.1.1.1.1r8rCc<eZdZdZdZeedZ d fd 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)rrENr/L F@c T|dd}|dd}tjdi|||i}tdi|} | D]I\} } | |vr@| || kr4| dkr.| |vr d| d| d} nd| d} t | J|| ||i}tdi|} d | vr'd | d D| d <| D]I\} } | |vr@| || kr4| dkr.| |vr d| d | d} nd | d} t | J|| |i}t d |i}t dtdi||_ tdi||_ ||_ ||_ ||_d|_d|_d|_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.id2labelc4i|]\}}t||Sr%)str).0keyvalues r7 z+GroupViTConfig.__init__..>s1333(2UCHHe333r8zv` 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%)popr&r'rto_dictitemsrOinfoupdaterCrrEprojection_dimprojection_intermediate_dimlogit_scale_init_valuer1r2output_segmentation)r4rrErnrorpr5r^r__text_config_dictrfrgmessage_vision_config_dictr6s r7r'zGroupViTConfig.__init__s1"::&8$??#ZZ(rrC sub_configsr'r@rAs@r7rYrYsw2J"4G[\\K$(% _)_)_)_)_)_)_)_)_)_)r8rYc eZdZedeeeeefffdZedeeeeefffdZede fdZ dddd ed ed e d deee ff fd Z edefdZxZS)GroupViTOnnxConfigreturnc Htddddfdddddd fd dddfgS) N input_idsbatchsequence)rr pixel_valuesrUheightwidth)rrr attention_maskrr4s r7inputszGroupViTOnnxConfig.inputsjsN'j99:WHQX!Y!YZ!w:#>#>?    r8cHtdddifdddifdddifdddifgS)Nlogits_per_imagerr{logits_per_text text_embeds image_embedsrrs r7outputszGroupViTOnnxConfig.outputstsI#a\2"QL1G -!W.     r8cdS)Ng-C6?r%rs r7atol_for_validationz&GroupViTOnnxConfig.atol_for_validationstr8N processorr batch_size seq_length frameworkrct|j|||}t|j||}i||S)N)rrr)rr)r&generate_dummy_inputs tokenizerimage_processor)r4rrrrtext_input_dictimage_input_dictr6s r7rz(GroupViTOnnxConfig.generate_dummy_inputssn ''77  J:Yb8  !7788  %* 9  7/6%566r8cdS)Nr%rs r7default_onnx_opsetz%GroupViTOnnxConfig.default_onnx_opsetsrr8)rrN)r:r;r<propertyrrdintrrfloatrrrrrr@rAs@r7rwrwisK  WS#X%6 67   X  gc3h&7!78   X UX ,0 7 7# 7 7 7 L) 7 c  7 7 7 7 7 7CXr8rw)rYrwrrCN)r= collectionsrcollections.abcrtypingrrrconfiguration_utilsr onnxr utilsr processing_utilsr r get_loggerr:rOrrCrYrw__all__r%r8r7rs#"############//////////333333$222222######  H % %Y3Y3Y3Y3Y3)Y3Y3Y3xi1i1i1i1i1+i1i1i1X|)|)|)|)|)%|)|)|)~++++++++\ a ` `r8