Zj  SSKJr SSKJr SSKJr SSKJrJr SSK J r J r \R"\ 5r\"SS 9\"S S \555r\"SS 9\"S S \555r\"SS 9\"SS\555r/SQrg))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)InstructBlipVideoVisionConfig!a  Example: ```python >>> from transformers import InstructBlipVideoVisionConfig, InstructBlipVideoVisionModel >>> # Initializing a InstructBlipVideoVisionConfig with Salesforce/instructblip-flan-t5-xl style configuration >>> configuration = InstructBlipVideoVisionConfig() >>> # Initializing a InstructBlipVideoVisionModel (with random weights) from the Salesforce/instructblip-flan-t5-xl style configuration >>> model = InstructBlipVideoVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```instructblipvideo_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#ږ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/instructblipvideo/configuration_instructblipvideo.pyrr!s 2J%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)!InstructBlipVideoQFormerConfigDa 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 InstructBlipVideoQFormerConfig, InstructBlipVideoQFormerModel >>> # Initializing a InstructBlipVideo Salesforce/instructblip-flan-t5-xl style configuration >>> configuration = InstructBlipVideoQFormerConfig() >>> # Initializing a model (with random weights) from the Salesforce/instructblip-flan-t5-xl style configuration >>> model = InstructBlipVideoQFormerModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```instructblipvideo_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$r%r&r'r(r)r*r:r+r,rrrrrr/r<r0r=r>r!rr@rArBr2r#r3r4r6r6Ds (-J&OJKs!!!s!J'**03 %#+3#&S&#u#!NE! L#* %&s&##r3r6c^\rSrSr%SrSrSS0r\\\ S.r Sr \ \ -S-\S'Sr\ \ -S-\S 'Sr\ \ -S-\S 'S r\\S 'S r\\S'Sr\\S'Sr\S-\S'U4SjrSrU=r$)InstructBlipVideoConfigna qformer_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`InstructBlipVideoQFormerConfig`]. num_query_tokens (`int`, *optional*, defaults to 32): The number of query tokens passed through the Transformer. Example: ```python >>> from transformers import ( ... InstructBlipVideoVisionConfig, ... InstructBlipVideoQFormerConfig, ... OPTConfig, ... InstructBlipVideoConfig, ... InstructBlipVideoForConditionalGeneration, ... ) >>> # Initializing a InstructBlipVideoConfig with Salesforce/instructblip-flan-t5-xl style configuration >>> configuration = InstructBlipVideoConfig() >>> # Initializing a InstructBlipVideoForConditionalGeneration (with random weights) from the Salesforce/instructblip-flan-t5-xl style configuration >>> model = InstructBlipVideoForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a InstructBlipVideoConfig from a InstructBlipVideoVisionConfig, InstructBlipVideoQFormerConfig and any PreTrainedConfig >>> # Initializing Instructblipvideo vision, Instructblipvideo Q-Former and language model configurations >>> vision_config = InstructBlipVideoVisionConfig() >>> qformer_config = InstructBlipVideoQFormerConfig() >>> text_config = OPTConfig() >>> config = InstructBlipVideoConfig(vision_config=vision_config, qformer_config=qformer_config, text_config=text_config) ```instructblipvideovideo_token_idvideo_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)z\qformer_config is None. Initializing the InstructBlipVideoQFormerConfig with default values.z``vision_config` is `None`. initializing the `InstructBlipVideoVisionConfig` with default values.r#)rIr loggerinfo isinstancedictgetr9r6rrrrBr)ruse_decoder_only_language_modelsuper __post_init__)selfkwargstext_model_type __class__s r4rV%InstructBlipVideoConfig.__post_init__sT    #-e46D  KKn o (($ / /"..22<GO-o>RAQAQRD     &"@"BD  KKv w ++T 2 2"@"W4CVCV"WD     %!>!@D  KKr **D 1 1!>!TASAS!TD 262D2D2P2P//3/?/?/J/JNo/o, ''r3)r9rIrTr)r$r%r&r'r(r) attribute_mapr r6r sub_configsrrRrr,r9rIrKr+rLr0r!rHrVr2 __classcell__)rZs@r4rDrDns" H%J%':;M!86K 59M4**T1859ND++d2926K((4/6c ###u#$(sTz(((r3rD)rDr6rN)huggingface_hub.dataclassesrconfiguration_utilsrmodels.auto.modeling_autorutilsrrautor r get_loggerr$rOrr6rD__all__r#r3r4rfs,/3J,-   H %?@$4AB?@%$%5%$A%$P?@N(.N(AN(b ir3