a  dfD@sdZddlZddlZddlmZddlmZddlmZe e Z ddd Z Gd d d eZ Gd d d eZGdddeZdS)z BridgeTower model configurationN)Union)PretrainedConfig)loggingzIhttps://huggingface.co/BridgeTower/bridgetower-base/blob/main/config.jsonzQhttps://huggingface.co/BridgeTower/bridgetower-base-itm-mlm/blob/main/config.json)zBridgeTower/bridgetower-basez$BridgeTower/bridgetower-base-itm-mlmc sDeZdZdZdZdfd d Zeeee j fddddZ Z S)BridgeTowerVisionConfiga This is the configuration class to store the vision configuration of a [`BridgeTowerModel`]. Instantiating a configuration with the defaults will yield a similar configuration to that of the bridgetower-base [BridgeTower/bridgetower-base](https://huggingface.co/BridgeTower/bridgetower-base/) 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. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in visual encoder model. patch_size (`int`, *optional*, defaults to 16): The size (resolution) of each patch. image_size (`int`, *optional*, defaults to 288): The size (resolution) of each image. initializer_factor (`float``, *optional*, defaults to 1): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. stop_gradient (`bool`, *optional*, defaults to `False`): Whether to stop gradient for training. share_layernorm (`bool`, *optional*, defaults to `True`): Whether LayerNorm layers are shared. remove_last_layer (`bool`, *optional*, defaults to `False`): Whether to remove the last layer from the vision encoder. Example: ```python >>> from transformers import BridgeTowerVisionConfig >>> # Initializing a BridgeTower BridgeTower/bridgetower-base style configuration for the vision model >>> configuration = BridgeTowerVisionConfig() >>> # Accessing the configuration >>> configuration ```Zbridgetower_vision_model r h㈵>FTc  sRtjfi| ||_||_||_||_||_||_||_||_ | |_ | |_ dSN) super__init__ hidden_sizenum_hidden_layers num_channels patch_size image_sizeinitializer_factorlayer_norm_eps stop_gradientshare_layernormremove_last_layer) selfrrrrrrrrrrkwargs __class__/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/transformers/models/bridgetower/configuration_bridgetower.pyrOsz BridgeTowerVisionConfig.__init__rpretrained_model_name_or_pathreturncKs||j|fi|\}}|ddkr,|d}d|vrjt|drj|d|jkrjtd|dd|jd|j|fi|SN model_type bridgetower text_configzYou are using a model of type z to instantiate a model of type zN. This is not supported for all configurations of models and can yield errors.Zget_config_dictgethasattrr$loggerwarning from_dictclsr!rZ config_dictrrrfrom_pretrainedis  z'BridgeTowerVisionConfig.from_pretrained) rrrr r r r FTF __name__ __module__ __qualname____doc__r$r classmethodrstrosPathLiker/ __classcell__rrrrr#s)rcsDeZdZdZdZdfdd Zeeee j fddddZ Z S)BridgeTowerTextConfiga This is the configuration class to store the text configuration of a [`BridgeTowerModel`]. The default values here are copied from RoBERTa. Instantiating a configuration with the defaults will yield a similar configuration to that of the bridgetower-base [BridegTower/bridgetower-base](https://huggingface.co/BridgeTower/bridgetower-base/) 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 50265): Vocabulary size of the text part of the model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`BridgeTowerModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. 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. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. max_position_embeddings (`int`, *optional*, defaults to 514): 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). type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the `token_type_ids`. initializer_factor (`float``, *optional*, defaults to 1): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. position_embedding_type (`str`, *optional*, defaults to `"absolute"`): Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155). For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658). is_decoder (`bool`, *optional*, defaults to `False`): Whether the model is used as a decoder or not. If `False`, the model is used as an encoder. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. classifier_dropout (`float`, *optional*): The dropout ratio for the classification head. Example: ```python >>> from transformers import BridgeTowerTextConfig >>> # Initializing a BridgeTower BridgeTower/bridgetower-base style configuration for the text model >>> configuration = BridgeTowerTextConfig() >>> # Accessing the configuration >>> configuration ```Zbridgetower_text_modelYrrr gelu皙?{Gz?r rabsoluteTNc stjfi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_||_||_||_dSr )rr vocab_sizerrnum_attention_heads hidden_actrintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangerposition_embedding_type use_cacheclassifier_dropout pad_token_id bos_token_id eos_token_id)rrCrrrDrrFrErGrHrIrJrKrrOrPrQrLrMrNrrrrrs(zBridgeTowerTextConfig.__init__rr cKs||j|fi|\}}|ddkr,|d}d|vrjt|drj|d|jkrjtd|dd|jd|j|fi|Sr#r'r-rrrr/s  z%BridgeTowerTextConfig.from_pretrained)r;rrrr r<r=r>r>r?r r@r r rrArBTNr0rrrrr:ys0A-r:c sBeZdZdZdZdfd d ZeeedddZ ddZ Z S)BridgeTowerConfiga This is the configuration class to store the configuration of a [`BridgeTowerModel`]. It is used to instantiate a BridgeTower 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 bridgetower-base [BridgeTower/bridgetower-base](https://huggingface.co/BridgeTower/bridgetower-base/) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: share_cross_modal_transformer_layers (`bool`, *optional*, defaults to `True`): Whether cross modal transformer layers are shared. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. initializer_factor (`float``, *optional*, defaults to 1): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. share_link_tower_layers (`bool`, *optional*, defaults to `False`): Whether the bride/link tower layers are shared. link_tower_type (`str`, *optional*, defaults to `"add"`): Type of the bridge/link layer. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. num_hidden_layers (`int`, *optional*, defaults to 6): Number of hidden layers in the Transformer encoder. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie input and output embeddings. init_layernorm_from_vision_encoder (`bool`, *optional*, defaults to `False`): Whether to init LayerNorm from the vision encoder. text_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`BridgeTowerTextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`BridgeTowerVisionConfig`]. Example: ```python >>> from transformers import BridgeTowerModel, BridgeTowerConfig >>> # Initializing a BridgeTower BridgeTower/bridgetower-base style configuration >>> configuration = BridgeTowerConfig() >>> # Initializing a model from the BridgeTower/bridgetower-base style configuration >>> model = BridgeTowerModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```r%Tr=rr r FaddrNc s|dd}|dd}tjfi|||_||_||_||_||_||_||_ ||_ | |_ | |_ | |_ | duri} td| duri} tdtfi| |_tfi| |_dS)NZtext_config_dictZvision_config_dictzV`text_config` is `None`. Initializing the `BridgeTowerTextConfig` with default values.zZ`vision_config` is `None`. Initializing the `BridgeTowerVisionConfig` with default values.)poprr$share_cross_modal_transformer_layersrErrrshare_link_tower_layerslink_tower_typerDrtie_word_embeddings"init_layernorm_from_vision_encoderr*infor:r&r vision_config)rrVrErrrrWrXrDrrYrZr&r\r_rrrr1s,    zBridgeTowerConfig.__init__r&r\cKs|f||d|S)z Instantiate a [`BridgeTowerConfig`] (or a derived class) from BridgeTower text model configuration. Returns: [`BridgeTowerConfig`]: An instance of a configuration object r^)to_dict)r.r&r\rrrrfrom_text_vision_configs^s z*BridgeTowerConfig.from_text_vision_configscCs8t|j}|j|d<|j|d<|jj|d<|S)z Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`]. Returns: `Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance, r&r\r$)copydeepcopy__dict__r&r_r\rr$)routputrrrr_is   zBridgeTowerConfig.to_dict) Tr=rr r FrSrrTFFNN) r1r2r3r4r$rr5r:rr`r_r9rrrrrRs(4- rR)r4rar7typingrZconfiguration_utilsrutilsrZ get_loggerr1r*Z)BRIDGETOWER_PRETRAINED_CONFIG_ARCHIVE_MAPrr:rRrrrrs    V