sgdZddlmZmZddlmZddlmZeje Z GddeZ Gdd eZ Gd d eZ Gd d eZGddeZy)zFLAVA model configurations)AnyDict)PretrainedConfig)loggingceZdZdZdZdZ ddededededed ed ed ed ed edededededeffd Z xZ 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 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 t|di|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_yN)super__init__r r rrrrrrrrrrrrr)selfr r rrrrrrrrrrrrrkwargs __class__s `/var/www/html/venv/lib/python3.12/site-packages/transformers/models/flava/configuration_flava.pyrzFlavaImageConfig.__init__Zs& "6"&!2#6 !2$#6 ,H)!2,$$(  $$) r& gelur){Gz?-q=rTT __name__ __module__ __qualname____doc__ model_typebase_config_keyintfloatboolr __classcell__r"s@r#r r s: x%J$O!##%!% %(.1#' %!#%#%#%! #%  #%  #%##%',#%!#%#%#%#%#%#%#% !#%#%r$r ceZdZdZdZdZ ddededededed ed ed ed ed ededededede ffd Z xZ S)FlavaTextConfigaC 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 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_configrtype_vocab_sizemax_position_embeddingsposition_embedding_typer r rrrrrrr pad_token_idrc t|di|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_yr)rrrr?r@rAr r rrrrrrrrrB)r rr?r@rAr r rrrrrrrrBrr!r"s r#rzFlavaTextConfig.__init__s& "6"$.'>$'>$&!2#6 !2$#6 ,H)!2,  (r$)i:wiabsoluter%r&r&r'r(r)r)r*r+rT) r0r1r2r3r4r5r6strr7r8rr9r:s@r#r<r<sE N$J#O  '*'1!##%!% %(.1#' %!#)#)#)"% #) "% #)  #)#)!#)#)#)##)',#)!#)#)#) !#)#)r$r<cpeZdZdZdZdZ ddededededed ed ed ed ed edeffd Z xZ 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 rrrrrrrr use_cls_tokenc  t |di| ||_||_||_||_||_||_||_||_ | |_ | |_ | |_ yr) rrr r rrrrrrrrrK)r r r rrrrrrrrrKr!r"s r#rzFlavaMultimodalConfig.__init__)sk "6"&!2#6 !2$#6 ,H)!2,  *r$) r%r&r'r(r)r)r*r+TTr/r:s@r#rHrHs2 h*J)O!"#%!% #&,/#' %"+++! +  +  +!+'*+!+++++r$rHcVeZdZdZdZ d dedededededed effd ZxZS) FlavaImageCodebookConfigflava_image_codebookimage_codebook_config num_groupsinput_channelsnum_blocks_per_groupr rfreezerc t |di|||_||_||_||_||_||_||_yr) rrrRrSrTr rrUr) r rRrSrTr rrUrr!r"s r#rz!FlavaImageCodebookConfig.__init__vsJ "6"$,$8!&$ !2r$)rrDr.Tr*) r0r1r2r4r5r6r7rr9r:s@r#rOrOGsx'J-O)Z$%#'333" 3  3  33!33r$rOc)eZdZdZdZeeeedZ dde e e fde e e fde e e fde e e fde d ed e d ed ed ede dededededededededef(fd ZededededefdZxZS) 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 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 ``` flava)r>r rJrQr r>rJrQr rprojection_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 |jdd}|jdd}|jdd}|jdd}t!|di|||i}tdi|j }|j D]A\}}||vs |||k7s|dvs||vr d|d|d}nd |d }t j|C|j|||i}tdi|j }d |vr3|d j Dcic]\}}t||c}}|d <|j D]A\}}||vs |||k7s|dvs||vr d|d |d}nd |d }t j|C|j|||i}tdi|j }|j D]A\}}||vs |||k7s|dvs||vr d|d|d}nd|d }t j|C|j|||i}tdi|j } | j D]A\}}||vs |||k7s|dvs||vr d|d|d}nd|d }t j|C|j| |i}t jd|i}t jd|i}t jd|i}t jdtdi||_ tdi||_tdi||_tdi||_||_||_||_||_| |_| |_d|_| |_| |_| |_||_||_||_||_||_||_ ||_!ycc}}w)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 overridden.id2labelzs` 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.?r)"poprrr<to_dictitemsloggerinfoupdater rFrHrOr r>rJrQr\r]r rrr^initializer_factorr_r`rarbrcrdrerfrgrh)"r r r>rJrQr rr\r]r^rr_r`rarbrcrdrerfrgrhr!rjrkrlrm_text_config_dictkeyvaluemessage_image_config_dict_multimodal_config_dict_image_codebook_config_dictr"s" r#rzFlavaConfig.__init__s6"::&8$?"JJ':DA!',Dd!K%+ZZ0Ld%S" "6"  '" !0 C2B C K K M 0557 ) U+%%;s3C*CSkHk..u%<T&U&]&]&_ #6;;= ) U,,!23!77#;;44u%TTWSXXqs VVYUZZqs KK(% )*  $ $%< = % 1$,(*%+C*`E_*`*h*h*j ':??A ) U00!6s!;;#;;88u%]]`\ab'' ]]`\aaxz KK(' ), " ( ()D E  L KKl m  K KKj k  $ "  KKv w ($& ! KKu -<|<*9[9!6!K9J!K%=%V@U%V",*&,!2&<#"%.$$)B&$ 0.+F(0P-&A2sN<c |d|j|j|j|jd|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 )r r>rJrQr)rs)clsr r>rJrQr!s r# from_configszFlavaConfig.from_configssP" %--/#++-/779"7"?"?"A     r$)NNNNr%r+r%Tg/L F@r*irqrqrqrqrqrqTTT)r0r1r2r3r4r<r rHrO sub_configsrrFrr6r7r8r classmethodrr9r:s@r#rZrZsCJJ&(2!9 K(,&*,004 %!"(.#'#+."%!$,015 +H'38nH'#s(^H' S> H' $CH~ H'  H'H'H'H'!&H'!H'H'H'H'$)H' !H'" #H'$%H'&&*'H'(+/)H'*+H'T & % 1  8   r$rZN)r3typingrrconfiguration_utilsrutilsr get_loggerr0rur r<rHrOrZrr$r#rsv!3   H %c%'c%Ln)&n)bS+,S+lA3/A3Ho "o r$