io9dZddlmZddlmZddlmZddlmZm 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| ||_||_||_||_||_||_| |_| |_ ||_ ||_ | |_ yN) super__init__ hidden_sizeintermediate_sizenum_hidden_layersnum_attention_heads patch_size image_sizeinitializer_rangeattention_dropoutlayer_norm_eps hidden_actqkv_bias)selfrrrrrrrrrrrkwargs __class__s w/mnt/e/genesis-system/.venv/lib/python3.12/site-packages/transformers/models/instructblip/configuration_instructblip.pyrz!InstructBlipVisionConfig.__init__Osi "6"&!2!2#6 $$!2!2,$  ) i'gelugư>gg|=T__name__ __module__ __qualname____doc__ model_typebase_config_keyr __classcell__rs@r r r sB0 d-J%O!!r!r cHeZdZdZdZdZ dfd ZxZS)InstructBlipQFormerConfiga7 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. 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|di|| |_||_||_||_||_||_||_||_ ||_ | |_ | |_ | |_ | |_||_yr)rr pad_token_id vocab_sizerrrrrhidden_dropout_probattention_probs_dropout_probmax_position_embeddingsrrcross_attention_frequencyencoder_hidden_size)rr7rrrrrr8r9r:rrr6r;r<rrs r rz"InstructBlipQFormerConfig.__init__s$ "6"($&!2#6 $!2#6 ,H)'>$!2,)B r!)i:wi r=i r'皙?r>i{Gz?g-q=rr"r(r0s@r r2r2msK7 r(J&O%( #"# !7!7r!r2cFeZdZdZdZddiZeeedZ dfd Z xZ S)InstructBlipConfigaP [`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(vision_config=vision_config, qformer_config=qformer_config, text_config=text_config) ``` instructblipimage_token_idimage_token_index) text_configr4r c |#td}tjdn0t|tr |j dd}t|di|}| t }tjdnt|tr t di|}| t}tjdnt|tr tdi|}||_||_ ||_ ||_ ||_ |jj|j_|jjt v|_d|_d|_t)|Tdi|y) NoptzTtext_config is None. Initializing the text config with default values (`OPTConfig`).r-zWqformer_config is None. Initializing the InstructBlipQFormerConfig with default values.z[`vision_config` is `None`. initializing the `InstructBlipVisionConfig` with default values.g?r?r)rloggerinfo isinstancedictgetr2r rFr r4num_query_tokensrErr<r-ruse_decoder_only_language_modelinitializer_factorrrr) rr r4rFrNrErtext_model_typers r rzInstructBlipConfig.__init__s1  (/1K KKn o  T *)oolEBO(9HKHK  !68N KKq r  -6HHN  46M KKu v  t ,4E}EM&*, 0!2262D2D2P2P//3/?/?/J/JNo/o,"%!% "6"r!)NNN N) r)r*r+r,r- attribute_maprr2r sub_configsrr/r0s@r rBrBsJ5 n J-M"31K &#&#r!rB)rBr2r N)r,configuration_utilsrmodels.auto.modeling_autorutilsrautorr get_loggerr)rIr r2rB__all__rr!r r[sb'3J-   H %Q!/Q!h^7 0^7Bh#)h#V Zr!