o iP8@sbdZddlmZddlmZeeZGdddeZGdddeZ Gdd d eZ gd Z d S) zBridgeTower model configuration)PretrainedConfig)loggingcs>eZdZdZdZdZ      dfd d ZZS)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 ```bridgetower_vision_model vision_config r h㈵>FTc  sRtjdi| ||_||_||_||_||_||_||_||_ | |_ | |_ dSN) super__init__ hidden_sizenum_hidden_layers num_channels patch_size image_sizeinitializer_factorlayer_norm_eps stop_gradientshare_layernormremove_last_layer) selfrrrrrrrrrrkwargs __class__rv/home/ubuntu/veenaModal/venv/lib/python3.10/site-packages/transformers/models/bridgetower/configuration_bridgetower.pyrFs z BridgeTowerVisionConfig.__init__) rrrr r r r FTF__name__ __module__ __qualname____doc__ model_typebase_config_keyr __classcell__rrrrrs*rcsLeZdZdZdZdZ           dfdd ZZS)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). 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 ```bridgetower_text_model text_configYrrr gelu皙?r absoluteTc s|tjdi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_| |_||_||_dSr )rr vocab_sizerrnum_attention_heads hidden_actrintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizerposition_embedding_type use_cache pad_token_id bos_token_id eos_token_id)rr3rrr4rr6r5r7r8r9r:rr=r>r?r;r<rrrrrs$ zBridgeTowerTextConfig.__init__)r+rrrr r,r-r.r.r/r r r r0r1r2Tr rrrrr(as,>r(csJeZdZdZdZeedZ      dfdd ZZ 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 ``` bridgetower)r*rTr-rr r FaddrNc s|dd}|dd}tjdi|||_||_||_||_||_||_||_ ||_ | |_ | |_ | |_ | durAi} td| durLi} tdtdi| |_tdi| |_dS)Ntext_config_dictvision_config_dictzV`text_config` is `None`. Initializing the `BridgeTowerTextConfig` with default values.zZ`vision_config` is `None`. Initializing the `BridgeTowerVisionConfig` with default values.r)poprr$share_cross_modal_transformer_layersr5rrrshare_link_tower_layerslink_tower_typer4rtie_word_embeddings"init_layernorm_from_vision_encoderloggerinfor(r*rr)rrGr5rrrrHrIr4rrJrKr*rr_rrrrs,    zBridgeTowerConfig.__init__) Tr-rr r FrBrrCFFNN) r!r"r#r$r%r(r sub_configsrr'rrrrr@s$5 r@)r@r(rN) r$configuration_utilsrutilsr get_loggerr!rLrr(r@__all__rrrrs   Il g