ZjSrSSKJr SSKJr SSKJr SSKJrJ r SSK J r J r \ R"\5r\"S S 9\"S S \555r\"S S 9\"S S\555r\"S S 9\"SS\555r/SQrg)z InstructBLIP model configuration)strict)PreTrainedConfig)!MODEL_FOR_CAUSAL_LM_MAPPING_NAMES)auto_docstringlogging)CONFIG_MAPPING AutoConfigz"Salesforce/instructblip-flan-t5-xl) checkpointc\rSrSr%SrSrSrSr\\ S'Sr \\ S'S r \\ S 'S r \\ S 'S r \\\-\\\4-\ S'Sr\\\-\\\4-\ S'Sr\\ S'Sr\\ S'Sr\\-\ S'Sr\\ S'Sr\\ S'Srg)InstructBlipVisionConfiga Example: ```python >>> from transformers import InstructBlipVisionConfig, InstructBlipVisionModel >>> # Initializing a InstructBlipVisionConfig with Salesforce/instructblip-flan-t5-xl style configuration >>> configuration = InstructBlipVisionConfig() >>> # Initializing a InstructBlipVisionModel (with random weights) from the Salesforce/instructblip-flan-t5-xl style configuration >>> model = InstructBlipVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```instructblip_vision_model vision_config hidden_sizeiintermediate_size'num_hidden_layersnum_attention_heads image_size patch_sizegelu hidden_actgư>layer_norm_epsgattention_dropoutg|=initializer_rangeTqkv_biasN)__name__ __module__ __qualname____firstlineno____doc__ model_typebase_config_keyrint__annotations__rrrrlisttuplerrstrrfloatr r!r"bool__static_attributes__r#ڌ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/instructblip/configuration_instructblip.pyrrs -J%OK!s!s!!47Jd3i%S/1746Jd3i%S/16J NE %(us{($u$Hdr3rc\rSrSr%SrSrSrSr\\ S'Sr \\ S'S r \\ S 'S r \\ S 'S r \\ S 'Sr\\ S'Sr\\-\ S'Sr\\-\ S'Sr\\ S'Sr\\ S'Sr\\ S'Sr\S-\ S'Sr\\ S'Sr\\ S'S rg)!InstructBlipQFormerConfig>a 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/instructblip-flan-t5-xl style configuration >>> configuration = InstructBlipQFormerConfig() >>> # Initializing a model (with random weights) from the Salesforce/instructblip-flan-t5-xl style configuration >>> model = InstructBlipQFormerModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```instructblip_qformerqformer_configi:w vocab_sizeir rri rrrg?hidden_dropout_probattention_probs_dropout_probimax_position_embeddings{Gz?r!g-q=rrN pad_token_idr cross_attention_frequencyrencoder_hidden_sizer#)r$r%r&r'r(r)r*r:r+r,rrrrrr/r<r0r=r>r!rr@rArBr2r#r3r4r6r6>s ((J&OJKs!!!s!J'**03 %#+3#&S&#u#!NE! L#* %&s&##r3r6c^\rSrSr%SrSrSS0r\\\ S.r Sr \ \ -S-\S'Sr\ \ -S-\S 'Sr\ \ -S-\S 'S r\\S 'Sr\S-\S'S r\\S'Sr\\S'U4SjrSrU=r$)InstructBlipConfighaY qformer_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`InstructBlipQFormerConfig`]. num_query_tokens (`int`, *optional*, defaults to 32): The number of query tokens passed through the Transformer. Example: ```python >>> from transformers import ( ... InstructBlipVisionConfig, ... InstructBlipQFormerConfig, ... OPTConfig, ... InstructBlipConfig, ... InstructBlipForConditionalGeneration, ... ) >>> # Initializing a InstructBlipConfig with Salesforce/instructblip-flan-t5-xl style configuration >>> configuration = InstructBlipConfig() >>> # Initializing a InstructBlipForConditionalGeneration (with random weights) from the Salesforce/instructblip-flan-t5-xl 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_configr9rNrr9rI num_query_tokensg?initializer_factorr?r!c ~>URc)[S"5Ul[RS5 OY[ UR[ 5(a:URR SS5n[U"S0URD6UlURc%[5Ul[RS5 O9[ UR[ 5(a[S0URD6UlURc%[5Ul [RS5 O9[ UR[ 5(a[S0URD6Ul URRURl URR[;Ul[ TU]D"S0UD6 g)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.r#)rIr loggerinfo isinstancedictgetr9r6rrrrBr)ruse_decoder_only_language_modelsuper __post_init__)selfkwargstext_model_type __class__s r4rV InstructBlipConfig.__post_init__sP    #-e46D  KKn o (($ / /"..22<GO-o>RAQAQRD     &";"=D  KKq r ++T 2 2";"Rd>Q>Q"RD     %!9!;D  KKu v **D 1 1!9!ODrfs'.3J,-   H %?@/AB?@%$ 0%$A%$P?@M()M(AM(` Zr3