a ½ ÀhP8ã@sbdZddlmZddlmZe e¡ZGdd„deƒZGdd„deƒZ Gdd „d eƒZ gd ¢Z d S) zBridgeTower model configurationé)ÚPretrainedConfig)Úloggingc s*eZdZdZdZdZd‡fd d„ Z‡ZS)ÚBridgeTowerVisionConfigaÇ 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_modelÚ vision_configéé réé éçñh㈵øä>FTc  sRtƒjfi| ¤Ž||_||_||_||_||_||_||_||_ | |_ | |_ dS©N) ÚsuperÚ__init__Ú hidden_sizeÚnum_hidden_layersÚ num_channelsÚ patch_sizeÚ image_sizeÚinitializer_factorÚlayer_norm_epsÚ stop_gradientÚshare_layernormÚremove_last_layer) ÚselfrrrrrrrrrrÚkwargs©Ú __class__©úu/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/bridgetower/configuration_bridgetower.pyrFsz BridgeTowerVisionConfig.__init__) rrrrr r r FTF©Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeZbase_config_keyrÚ __classcell__rrrrrs*õrcs*eZdZdZdZdZd‡fdd„ Z‡ZS)ÚBridgeTowerTextConfiga´ 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). 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://huggingface.co/papers/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://huggingface.co/papers/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`. 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_modelÚ text_configéYÄrrr é Úgeluçš™™™™™¹?ér ééÚabsoluteTc s|tƒjfi|¤Ž||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_| |_||_||_dSr )r rÚ vocab_sizerrÚnum_attention_headsÚ hidden_actrÚintermediate_sizeÚhidden_dropout_probÚattention_probs_dropout_probÚmax_position_embeddingsÚtype_vocab_sizerÚposition_embedding_typeÚ use_cacheÚ pad_token_idÚ bos_token_idÚ eos_token_id)rr0rrr1rr3r2r4r5r6r7rr:r;r<r8r9rrrrr£s$zBridgeTowerTextConfig.__init__)r(rrrr r)r*r+r+r,r r r r-r.r/Trrrrrr&as*>îr&c s0eZdZdZdZeedœZd‡fdd„ Z‡Z S)ÚBridgeTowerConfiga~ 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 ```Z bridgetower)r'rTr*rr r FÚaddréNc s¼| dd¡}| dd¡}tƒjfi|¤Ž||_||_||_||_||_||_||_ ||_ | |_ | |_ | |_ | dur‚i} t d¡| dur˜i} t d¡tfi| ¤Ž|_tfi| ¤Ž|_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.)Úpopr rÚ$share_cross_modal_transformer_layersr2rrrÚshare_link_tower_layersÚlink_tower_typer1rÚtie_word_embeddingsÚ"init_layernorm_from_vision_encoderÚloggerÚinfor&r'rr)rrAr2rrrrBrCr1rrDrEr'rrÚ_rrrrs,    zBridgeTowerConfig.__init__) Tr*rr r Fr>rr?FFNN) r r!r"r#r$r&rZ sub_configsrr%rrrrr=Ís"5 òr=)r=r&rN) r#Zconfiguration_utilsrÚutilsrZ get_loggerr rFrr&r=Ú__all__rrrrÚs   Ilg