T^(h=dZddlmZddlmZddlmZddlmZm Z eje Z GddeZ Gd d eZGd d eZgd Zy)z InstructBLIP model configuration)PretrainedConfig)!MODEL_FOR_CAUSAL_LM_MAPPING_NAMES)logging)CONFIG_MAPPING AutoConfigcBeZdZdZdZdZ dfd ZxZS)InstructBlipVisionConfigaW This is the configuration class to store the configuration of a [`InstructBlipVisionModel`]. It is used to instantiate a InstructBLIP vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration defaults will yield a similar configuration to that of the InstructBLIP [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5) 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 1408): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 6144): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. num_hidden_layers (`int`, *optional*, defaults to 39): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 14): The size (resolution) of each patch. 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"` `"gelu"` are supported. to 1e-5): The epsilon used by the layer normalization layers. layer_norm_eps (`float`, *optional*, defaults to 1e-06): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 1e-10): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries and values in the self-attention layers. Example: ```python >>> from transformers import InstructBlipVisionConfig, InstructBlipVisionModel >>> # Initializing a InstructBlipVisionConfig with Salesforce/instruct-blip-flan-t5 style configuration >>> configuration = InstructBlipVisionConfig() >>> # Initializing a InstructBlipVisionModel (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration >>> model = InstructBlipVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```instructblip_vision_model vision_configc  t |di| ||_||_||_||_||_||_| |_| |_ ||_ ||_ | |_ y)N) super__init__ hidden_sizeintermediate_sizenum_hidden_layersnum_attention_heads patch_size image_sizeinitializer_rangeattention_dropoutlayer_norm_eps hidden_actqkv_bias)selfrrrrrrrrrrrkwargs __class__s y/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/instructblip/configuration_instructblip.pyrz!InstructBlipVisionConfig.__init__Psi "6"&!2!2#6 $$!2!2,$  ) i'gelugư>gg|=T__name__ __module__ __qualname____doc__ model_typebase_config_keyr __classcell__rs@rr r sB0 d-J%O!!r r cJeZdZdZdZdZ dfd ZxZS)InstructBlipQFormerConfiga This is the configuration class to store the configuration of a [`InstructBlipQFormerModel`]. It is used to instantiate a InstructBLIP Querying Transformer (Q-Former) 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 InstructBLIP [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Note that [`InstructBlipQFormerModel`] is very similar to [`BertLMHeadModel`] with interleaved cross-attention. Args: vocab_size (`int`, *optional*, defaults to 30522): Vocabulary size of the Q-Former model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling the model. 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 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). 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. pad_token_id (`int`, *optional*, defaults to 0): Token id used for padding sequences. 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). cross_attention_frequency (`int`, *optional*, defaults to 2): The frequency of adding cross-attention to the Transformer layers. encoder_hidden_size (`int`, *optional*, defaults to 1408): The hidden size of the hidden states for cross-attention. Examples: ```python >>> from transformers import InstructBlipQFormerConfig, InstructBlipQFormerModel >>> # Initializing a InstructBLIP Salesforce/instruct-blip-flan-t5 style configuration >>> configuration = InstructBlipQFormerConfig() >>> # Initializing a model (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration >>> model = InstructBlipQFormerModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```instructblip_qformerqformer_configc t|dd| i|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_y)N pad_token_idr)rr vocab_sizerrrrrhidden_dropout_probattention_probs_dropout_probmax_position_embeddingsrrposition_embedding_typecross_attention_frequencyencoder_hidden_size)rr6rrrrrr7r8r9rrr5r:r;r<rrs rrz"InstructBlipQFormerConfig.__init__s& =l=f=$&!2#6 $!2#6 ,H)'>$!2,'>$)B r )i:wi r=i r&皙?r>i{Gz?g-q=absoluterr!r'r/s@rr1r1nsN= ~(J&O%( # *"# !"7"7r r1c\eZdZdZdZeeedZ d fd Z e dedede fdZ xZ S) InstructBlipConfiga@ [`InstructBlipConfig`] is the configuration class to store the configuration of a [`InstructBlipForConditionalGeneration`]. It is used to instantiate a InstructBLIP model according to the specified arguments, defining the vision model, Q-Former model and language model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the InstructBLIP [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`InstructBlipVisionConfig`]. qformer_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`InstructBlipQFormerConfig`]. text_config (`dict`, *optional*): Dictionary of configuration options used to initialize any [`PretrainedConfig`]. num_query_tokens (`int`, *optional*, defaults to 32): The number of query tokens passed through the Transformer. image_token_index (`int`, *optional*): Token index of special image token. kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import ( ... InstructBlipVisionConfig, ... InstructBlipQFormerConfig, ... OPTConfig, ... InstructBlipConfig, ... InstructBlipForConditionalGeneration, ... ) >>> # Initializing a InstructBlipConfig with Salesforce/instruct-blip-flan-t5 style configuration >>> configuration = InstructBlipConfig() >>> # Initializing a InstructBlipForConditionalGeneration (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration >>> model = InstructBlipForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a InstructBlipConfig from a InstructBlipVisionConfig, InstructBlipQFormerConfig and any PretrainedConfig >>> # Initializing InstructBLIP vision, InstructBLIP Q-Former and language model configurations >>> vision_config = InstructBlipVisionConfig() >>> qformer_config = InstructBlipQFormerConfig() >>> text_config = OPTConfig() >>> config = InstructBlipConfig.from_text_vision_configs(vision_config, qformer_config, text_config) ``` instructblip) text_configr3r c t|di||i}tjd|i}tjd|i}tjdt di||_t di||_d|vr|dnd}t|di||_ ||_ ||_ |j j|j_ |jjtv|_d|_d|_y) NzUvision_config is None. initializing the InstructBlipVisionConfig with default values.zWqformer_config is None. Initializing the InstructBlipQFormerConfig with default values.zTtext_config is None. Initializing the text config with default values (`OPTConfig`).r,optg?r?r)rrloggerinfor r r1r3rrEnum_query_tokensimage_token_indexrr<r,ruse_decoder_only_language_modelinitializer_factorr) rr r3rErJrKrtext_model_typers rrzInstructBlipConfig.__init__s "6"  M KKo p  !N KKq r  K KKn o5F F7I.I7C{7R+l3X])/:I[I 0!2262D2D2P2P//3/?/?/J/JNo/o,"%!%r r r3rEc n|d|j|j|jd|S)z Instantiate a [`InstructBlipConfig`] (or a derived class) from a InstructBLIP vision model, Q-Former and language model configurations. Returns: [`InstructBlipConfig`]: An instance of a configuration object )r r3rEr)to_dict)clsr r3rErs r from_vision_qformer_text_configsz3InstructBlipConfig.from_vision_qformer_text_configs8sD  '//1)113#++-    r )NNN N)r(r)r*r+r,rr1r sub_configsr classmethodrrRr.r/s@rrCrCsg5 n J!31K !&F / 2 &   r rC)rCr1r N)r+configuration_utilsrmodels.auto.modeling_autorutilsrautorr get_loggerr(rHr r1rC__all__rr rr\sb'3J-   H %Q!/Q!he7 0e7Pw )w t Zr