o ei@sdZddlmZddlmZddlmZeeZ GdddeZ Gdd d eZ Gd d d eZ Gd d d eZ GdddeZgdZdS)zFLAVA model configurations)Any)PreTrainedConfig)loggingcseZdZdZdZdZ          d!dededededededededededededededeffdd Z Z S)"FlavaImageConfiga This is the configuration class to store the configuration of a [`FlavaImageModel`]. It is used to instantiate an FLAVA 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 FLAVA [facebook/flava-full](https://huggingface.co/facebook/flava-full) 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 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" (i.e., feed-forward) layer in the Transformer encoder. 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"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`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. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. 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. num_channels (`int`, *optional*, defaults to 3): The number of input channels. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys and values. mask_token (`bool`, *optional*, defaults to `True`): Whether to use a mask token or not. Used in MIM (Masked Image Modeling) loss for FLAVA. vocab_size (`int`, *optional*, defaults to 8192): Vocabulary size of the [`FlavaImageCodebook`] used in conjunction with [`FlavaImageModel`] for MIM (Masked Image Modeling) loss for FLAVA. Example: ```python >>> from transformers import FlavaImageConfig, FlavaImageModel >>> # Initializing a FlavaImageModel with style configuration >>> configuration = FlavaImageConfig() >>> # Initializing a FlavaImageModel model (with random weights) from the style configuration >>> model = FlavaImageModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```flava_image_model image_config gelu{Gz?-q=rT hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangelayer_norm_eps image_size patch_size num_channelsqkv_bias mask_token vocab_sizec sptjdi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_dSN)super__init__rrrrrrrrrrrrrr r!)selfrrrrrrrrrrrrrr r!kwargs __class__r#k/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/flava/configuration_flava.pyr%Ys  zFlavaImageConfig.__init__)r r r r r r r rrrrrTTr __name__ __module__ __qualname____doc__ model_typebase_config_keyintfloatboolr% __classcell__r#r#r(r*rsd<     rcseZdZdZdZdZ        d dededededededededededededede ffdd Z Z S)!FlavaTextConfiga This is the configuration class to store the configuration of a [`FlavaTextModel`]. It is used to instantiate an FLAVA 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 FLAVA [facebook/flava-full](https://huggingface.co/facebook/flava-full) 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 30522): Vocabulary size of the BERT model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`FlavaTextModel`]. type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the `token_type_ids` passed when calling [`FlavaTextModel`]. Note that even though text encoder allows `token_type_ids`'s value as 2, for text-only pretraining and fine-tuning, only 1 is used similar to RoBERTa. max_position_embeddings (`int`, *optional*, defaults to 512): 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). For VL, max_length passed to model is 77. 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" (i.e., feed-forward) layer in the Transformer encoder. 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"` 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. 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-12): The epsilon used by the layer normalization layers. 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. num_channels (`int`, *optional*, defaults to 3): The number of input channels. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys and values. Example: ```python >>> from transformers import FlavaTextConfig, FlavaTextModel >>> # Initializing a FlavaTextModel with style configuration >>> configuration = FlavaTextConfig() >>> # Initializing a FlavaTextModel model (with random weights) from the style configuration >>> model = FlavaTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```flava_text_model text_config:wr r r r r rrrTr!type_vocab_sizemax_position_embeddingsrrrrrrrrr pad_token_idrc sjtjdi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_| |_dSr")r$r%r!r<r=rrrrrrrrrrr>)r&r!r<r=rrrrrrrrrr>rr'r(r#r*r%s zFlavaTextConfig.__init__)r9r:r;r r r r r r r rrrT) r,r-r.r/r0r1r2strr3r4r%r5r#r#r(r*r6s^A     r6csneZdZdZdZdZ      dd ededededededededededeffdd Z Z S)FlavaMultimodalConfiga This is the configuration class to store the configuration of a [`FlavaMultimodalModel`]. It is used to instantiate an FLAVA 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 FLAVA [facebook/flava-full](https://huggingface.co/facebook/flava-full) 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 6): 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" (i.e., feed-forward) layer in the Transformer encoder. 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"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`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. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys and values. use_cls_token (`bool`, *optional*, defaults to `True`): Whether to use an extra CLS token for multimodal settings. Usually needed by the FLAVA model. Example: ```python >>> from transformers import FlavaMultimodalConfig, FlavaMultimodalModel >>> # Initializing a FlavaMultimodalModel with style configuration >>> configuration = FlavaMultimodalConfig() >>> # Initializing a FlavaMultimodalModel model (with random weights) from the style configuration >>> model = FlavaMultimodalModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```flava_multimodal_modelmultimodal_configr r r r r rrTrrrrrrrrrr use_cls_tokenc  sXtjdi| ||_||_||_||_||_||_||_||_ | |_ | |_ | |_ dSr") r$r%rrrrrrrrrrrD) r&rrrrrrrrrrrDr'r(r#r*r% s zFlavaMultimodalConfig.__init__) r rCr r r r r rrTTr+r#r#r(r*r@sL4    r@csTeZdZdZdZ       dd ed ed ed edededeffdd ZZS)FlavaImageCodebookConfigflava_image_codebookimage_codebook_configrr:rTr num_groupsinput_channelsnum_blocks_per_grouprr!freezerc  s@tjdi|||_||_||_||_||_||_||_dSr") r$r%rJrKrLrr!rMr) r&rJrKrLrr!rMrr'r(r#r*r%ms  z!FlavaImageCodebookConfig.__init__)rHrr:rIrTr) r,r-r.r0r1r2r3r%r5r#r#r(r*rE>s4-rEc,seZdZdZdZeeeedZ             d#d e e e fdBd e e e fdBde e e fdBde e e fdBde dede dededede dededededededededed edBf*fd!d" ZZS)$ FlavaConfiga$ [`FlavaConfig`] is the configuration class to store the configuration of a [`FlavaModel`]. It is used to instantiate FLAVA model according to the specified arguments, defining the text model, image model, image codebook and multimodal model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the FLAVA [facebook/flava-full](https://huggingface.co/facebook/flava-full) 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 [`FlavaTextConfig`]. image_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`FlavaImageConfig`]. multimodal_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`FlavaMultimodalConfig`]. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. projection_dim (`int`, *optional*, defaults to 512): Dimensionality of text and image 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 FLAVA/CLIP implementation. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. ce_ignore_index (`int`, *optional*, defaults to -100): Cross entropy index to ignore. mim_weight (`float`, *optional*, defaults to 1.0): Weight to be assigned to MIM (Masked Image Modeling) unimodal loss mlm_weight (`float`, *optional*, defaults to 1.0): Weight to be assigned to MLM (Masked Language Modeling) unimodal loss global_contrastive_weight (`float`, *optional*, defaults to 1.0): Weight to be assigned to global contrastive cross-alignment loss. itm_weight (`float`, *optional*, defaults to 1.0): Weight to be assigned to image-text matching multimodal loss. mmm_image_weight (`float`, *optional*, defaults to 1.0): Weight to be assigned to MMM loss's image part. mmm_text_weight (`float`, *optional*, defaults to 1.0): Weight to be assigned to MMM loss's text part. global_backprop_contrastive (`bool`, *optional*, defaults to `True`): Whether to use global backpropgation through all workers in contrastive loss. skip_unmasked_multimodal_encoder (`bool`, *optional*, defaults to `True`): Whether to skip running unmasked multimodal encoder whose outputs are not used by FLAVA losses. return_loss (`bool`, *optional*, defaults to `True`): Whether to return loss or not tie_word_embeddings (`bool`, *optional*, defaults to `True`): Whether to tie weight embeddings Example: ```python >>> from transformers import FlavaConfig, FlavaModel, FlavaForPreTraining >>> # Initializing a FlavaConfig with style configuration >>> configuration = FlavaConfig() >>> # Initializing a FlavaModel and FlavaForPreTraining model (with random weights) from the style configuration >>> model = FlavaModel(configuration) >>> model_pre = FlavaForPreTraining(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> configuration_pre = model_pre.config ``` flava)r8rrBrGNr rT/L F@r?rr8rBrGrrprojection_dim init_codebooklogit_scale_init_valuerce_ignore_index mim_weight mlm_weightglobal_contrastive_weight itm_weightmmm_image_weightmmm_text_weightglobal_backprop_contrastive skip_unmasked_multimodal_encoder return_losstie_word_embeddingsc" s|dd}|dd}|dd}|dd}|dur`|dur"i}tdi|}|D]+\}}||vrZ|||krZ|dkrZ||vrOd|d|d}nd |d }t|q/|||dur|durji}tdi|}d |vrd d |d D|d <|D]+\}}||vr|||kr|dkr||vrd|d|d}nd|d }t|q|||dur|duri}tdi|} | D]+\}}||vr|||kr|dkr||vrd|d|d}nd|d }t|q|| |durQ|duri}t di|}!|!D]0\}}||vrJ|||krJ|dkrJ||vr?d|d|d}nd|d }t|q||!|dur_t}tdn t |t rltdi|}|durzt}tdn t |t rtdi|}|durt}tdn t |t rtdi|}|durt }tdn t |t rt di|}||_ ||_ ||_||_||_||_||_||_| |_| |_d|_| |_| |_| |_||_||_||_||_||_||_||_ ||_!t"j#di|dS)Ntext_config_dictimage_config_dictmultimodal_config_dictimage_codebook_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.zk`text_config_dict` is provided which will be used to initialize `FlavaTextConfig`. The value `text_config["z"]` will be overridden.id2labelcSsi|] \}}t||qSr#)r?).0keyvaluer#r#r* sz(FlavaConfig.__init__..zs` is found in both `image_config_dict` and `image_config` but with different values. The value `image_config_dict["zn`image_config_dict` is provided which will be used to initialize `FlavaImageConfig`. The value `image_config["z` is found in both `multimodal_config_dict` and `multimodal_config` but with different values. The value `multimodal_config_dict["z}`multimodal_config_dict` is provided which will be used to initialize `FlavaMultimodalConfig`. The value `multimodal_config["z` is found in both `image_codebook_config_dict` and `image_codebook_config` but with different values. The value `image_codebook_config_dict["z`image_codebook_config_dict` is provided which will be used to initialize `FlavaImageCodebookConfig`. The value `image_codebook_config["zP`text_config` is `None`. initializing the `FlavaTextConfig` with default values.zR`image_config` is `None`. initializing the `FlavaImageConfig` with default values.zW`image_config` is `None`. initializing the `FlavaMultimodalConfig` with default values.zZ`image_config` is `None`. initializing the `FlavaImageCodebookConfig` with default values.rRr#)$popr6to_dictitemsloggerinfoupdaterr@rE isinstancedictr8rrBrGrSrTrrrrUinitializer_factorrVrWrXrYrZr[r\r]r^r_r`r$r%)"r&rr8rBrGrrrSrTrUrrVrWrXrYrZr[r\r]r^r_r`r'rarbrcrd_text_config_dictrirjmessage_image_config_dict_multimodal_config_dict_image_codebook_config_dictr(r#r*r%s                                zFlavaConfig.__init__)NNNNr rr TrPrrQrRrRrRrRrRrRTTTT)r,r-r.r/r0r6rr@rE sub_configsrsr?rr2r3r4r%r5r#r#r(r*rNsD      rN)rNrErr@r6N)r/typingrconfiguration_utilsrutilsr get_loggerr,rorr6r@rErN__all__r#r#r#r*s    fiVD