o h{@sdZddlZddlmZmZmZddlmZddlm Z e e Z ddiZ Gd d d eZGd d d eZGd ddeZGdddeZGdddeZdS)z FLAVA model configurationsN)AnyDictUnion)PretrainedConfig)loggingzfacebook/flava-fullzChttps://huggingface.co/facebook/flava-full/resolve/main/config.jsoncseZdZdZdZ         d%dededededededededededededededeffdd Ze d e e e j fd!d"fd#d$ZZS)&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 probabilitiy 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 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__rrrrrrrrrrrrr r!r")selfrrrrrrrrrrrrr r!r"kwargs __class__r$c/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/flava/configuration_flava.pyr&^  zFlavaImageConfig.__init__pretrained_model_name_or_pathreturnrcK|||j|fi|\}}|ddkr|d}d|vr:t|dr:|d|jkr:td|dd|jd|j|fi|S)N model_typeflava image_configYou are using a model of type to instantiate a model of type N. This is not supported for all configurations of models and can yield errors._set_token_in_kwargsget_config_dictgethasattrr0loggerwarning from_dictclsr-r( config_dictr$r$r+from_pretrained   z FlavaImageConfig.from_pretrained)r r r r r rrrrrrrTTr__name__ __module__ __qualname____doc__r0intfloatboolr& classmethodrstrosPathLikerA __classcell__r$r$r)r+rsf<     %&rcseZdZdZdZ         d&dededededededededededededededeffdd Z e d!e ee j fd"d#fd$d%ZZS)'FlavaTextConfigaD 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. 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). 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 probabilitiy 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:wabsoluter r r r rrrrTr"type_vocab_sizemax_position_embeddingsposition_embedding_typerrrrrrrrr pad_token_idr c sptjdi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_dSr#)r%r&r"rVrWrXrrrrrrrrrr rY)r'r"rVrWrXrrrrrrrrrrYr r(r)r$r+r&r,zFlavaTextConfig.__init__r-r.rcKr/)Nr0r1 text_configr3r4r5r6r>r$r$r+rArBzFlavaTextConfig.from_pretrained)rRrSrTrUr r r r r rrrrrT)rDrErFrGr0rHrLrIrJr&rKrrMrNrArOr$r$r)r+rPsfG     %&rPcseZdZdZdZ        dd ed edededededededededeffdd Ze de e e j fddfddZZS)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 probabilitiy 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_modelr r r r rrrTrrrrrrrrrr use_cls_tokenc  sXtjdi| ||_||_||_||_||_||_||_||_ | |_ | |_ | |_ dSr#) r%r&rrrrrrrrrr r^) r'rrrrrrrrrr r^r(r)r$r+r&Os zFlavaMultimodalConfig.__init__r-r.rcKr/)Nr0r1multimodal_configr3r4r5r6r>r$r$r+rAlrBz%FlavaMultimodalConfig.from_pretrained) r r]r r r rrrrTTrCr$r$r)r+r[sN4    &r[cspeZdZdZ       dd ed ed ed ed ededeffdd Zedee e j fddfddZ Z S)FlavaImageCodebookConfigflava_image_codebookrrSrTr num_groupsinput_channelsnum_blocks_per_grouprr"freezerc  s@tjdi|||_||_||_||_||_||_||_dSr#) r%r&rdrerfrr"rgr) r'rdrerfrr"rgrr(r)r$r+r&s  z!FlavaImageCodebookConfig.__init__r-r.rcKr/)Nr0r1image_codebook_configr3r4r5r6r>r$r$r+rArBz(FlavaImageCodebookConfig.from_pretrained)rbrrSrcrTr)rDrErFr0rHrIr&rKrrLrMrNrArOr$r$r)r+r`s6-&r`c)seZdZdZdZ             d#d eeefd eeefd eeefdeeefdede dede de de dede de de de de de de de de f(fdd Z e d e d ed edefd!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): Dimentionality of text and image projection layers. logit_scale_init_value (`float`, *optional*, defaults to 2.6592): The inital value of the *logit_scale* paramter. 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 kwargs (*optional*): Dictionary of keyword arguments. 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 ``` r1Nr rT/L F@r?r2rZr_rhrrprojection_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_lossc! s|dd}|dd}|dd}|dd}tjdi||duri|dur+i}tdi|}|D]+\}}||vrc|||krc|dvrc||vrXd|d|d}nd |d }t|q8|||dur|dursi}t di|}d |vrd d |d D|d <|D]+\}}||vr|||kr|dvr||vrd|d|d}nd|d }t|q|||dur|duri}t di|}|D].\}}||vr|||kr|dvr||vrd|d|d}nd|d }t|q|||dur]|duri}t di|} | D]0\}}||vrV|||krV|dvrV||vrKd|d|d}nd|d }t|q'|| |durii}t d|durui}t d|duri}t d|duri}t dt di||_ tdi||_t di||_t di||_||_||_||_||_| |_| |_d|_| |_| |_| |_||_||_||_||_||_||_ ||_!dS)Ntext_config_dictimage_config_dictmultimodal_config_dictimage_codebook_config_dict)transformers_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 overriden.id2labelcSsi|] \}}t||qSr$)rL).0keyvaluer$r$r+ dsz(FlavaConfig.__init__..zs` is found in both `image_config_dict` and `image_config` but with different values. The value `image_config_dict["zn`image_config_dict` is provided which will be used to initialize `FlavaImageConfig`. The value `image_config["z` is found in both `multimodal_config_dict` and `multimodal_config` but with different values. The value `multimodal_config_dict["z}`multimodal_config_dict` is provided which will be used to initialize `FlavaMultimodalConfig`. The value `multimodal_config["z` is found in both `image_codebook_config_dict` and `image_codebook_config` but with different values. The value `image_codebook_config_dict["z`image_codebook_config_dict` is provided which will be used to initialize `FlavaImageCodebookConfig`. The value `image_codebook_config["zR`image_config` is `None`. initializing the `FlavaImageConfig` with default values.zP`text_config` is `None`. Initializing the `FlavaTextConfig` with default values.z\`multimodal_config` is `None`. initializing the `FlavaMultimodalConfig` with default values.zc`image_codebook_config` is `None`. initializing the `FlavaImageCodebookConfig` with default values.rlr$)"popr%r&rPto_dictitemsr;r<updaterr[r`infor2rZr_rhrmrnrrrroinitializer_factorrprqrrrsrtrurvrwrxry)!r'r2rZr_rhrrrmrnrorrprqrrrsrtrurvrwrxryr(rzr{r|r}_text_config_dictrrmessage_image_config_dict_multimodal_config_dict_image_codebook_config_dictr)r$r+r&s                              zFlavaConfig.__init__cKs(|d||||d|S)a& Instantiate a [`FlavaConfig`] (or a derived class) from flava text model configuration, flava image model configuration, flava multimodal model and flava codebook model configuration. Returns: [`FlavaConfig`]: An instance of a configuration object )r2rZr_rhNr$)r)r?r2rZr_rhr(r$r$r+ from_configsszFlavaConfig.from_configs)NNNNr rr TrjrrkrlrlrlrlrlrlTTT)rDrErFrGr0rrLrrHrIrJr&rKrrPr[r`rrOr$r$r)r+risE         Kri)rGrMtypingrrrconfiguration_utilsrutilsr get_loggerrDr;#FLAVA_PRETRAINED_CONFIG_ARCHIVE_MAPrrPr[r`rir$r$r$r+s   wgU