+ j ^RIHt^RIHt^RIHt^RIHtHt^RI H t H t ]P!] 4t]!RR7]!RR ]444t]!RR7]!R R ]444t]!RR7]!R R ]444t.ROtR#))strict)PreTrainedConfig)!MODEL_FOR_CAUSAL_LM_MAPPING_NAMES)auto_docstringlogging)CONFIG_MAPPING AutoConfigz"Salesforce/instructblip-flan-t5-xl) checkpointcda]tRt^!toRtRtRtRtRt^'t ^t ^t ^t Rt RtRtR tR tV3R ltR tVtR #)InstructBlipVideoVisionConfiga  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_configigelugư>gg|=Tc:<V^8dQh/S[;R&S[;R&S[;R&S[;R&S[S[S[,,S[S[S[3,,;R&S[S[S[,,S[S[S[3,,;R&S[;R&S[;R&S[S[,;R &S[;R &S[;R &#)  hidden_sizeintermediate_sizenum_hidden_layersnum_attention_heads image_size patch_size hidden_actlayer_norm_epsattention_dropoutinitializer_rangeqkv_bias)intlisttuplestrfloatbool)format __classdict__s"چ/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/instructblipvideo/configuration_instructblipvideo.py __annotate__*InstructBlipVideoVisionConfig.__annotate__!s,-.!/012!34d3i%S/1756d3i%S/16789: ;<s{(=>$?@AN)__name__ __module__ __qualname____firstlineno____doc__ model_typebase_config_keyrrrrrrrrrrr__annotate_func____static_attributes____classdictcell__r%s@r&r r !sZ 2J%OK!!47J46JJ N%($HAr)r cpa]tRt^DtoRtRtRtRtRt^ t ^ t Rt Rt Rt RtR tR tR t^t^tR tV3R ltRtVtR#)InstructBlipVideoQFormerConfiga 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:wii rg?i{Gz?g-q=rc<V^8dQh/S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[S[,;R&S[S[,;R&S[;R &S[;R &S[;R &S[R ,;R &S[;R&S[;R&#)r vocab_sizerrrrrhidden_dropout_probattention_probs_dropout_probmax_position_embeddingsrrN pad_token_idcross_attention_frequencyencoder_hidden_size)rr!r")r$r%s"r&r'+InstructBlipVideoQFormerConfig.__annotate__Ds456789:!;<!=>?@*AB#(#+3CD!&EF#GH!IJ* KL #&MN#Or)r*N)r+r,r-r.r/r0r1r<rrrrrr=r>r?rrr@rArBr2r3r4r5s@r&r7r7Dsm (-J&OJK!!J'*03 #&#!N L%&#Or)r7czaa]tRt^ntoRtRtRR/tR]R]R] /t Rt Rt Rt ^ tR tR tRtV3R ltV3R ltR tVtV;t#)InstructBlipVideoConfiga 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_configr9rNg?r:c <VPf.\R,!4Vn\PR4M^\ VP\ 4'd?VPP RR4p\V,!R/VPBVnVPf&\4Vn\PR4M:\ VP\ 4'd\R/VPBVnVPf&\4Vn \PR4M:\ VP\ 4'd\R/VPBVn VPPVPn VPP\9Vn\ SV`D!R/VBR#)NoptzTtext_config is None. Initializing the text config with default values (`OPTConfig`).r0z\qformer_config is None. Initializing the InstructBlipVideoQFormerConfig with default values.z``vision_config` is `None`. initializing the `InstructBlipVideoVisionConfig` with default values.r*)rIrloggerinfo isinstancedictgetr9r7rr rrBr0ruse_decoder_only_language_modelsuper __post_init__)selfkwargstext_model_type __class__s&, r&rS%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, ''r)c<V^8dQh/S[S[,R,;R&S[S[,R,;R&S[S[,R,;R&S[;R&S[;R&S[;R&S[R,;R&#) rNrr9rInum_query_tokensinitializer_factorrrH)rOrrr")r$r%s"r&r'$InstructBlipVideoConfig.__annotate__ns`**T18ab++d29cd((4/6efgh#ij#klTz(mr))r9rIrQr)r+r,r-r.r/r0 attribute_mapr r7r sub_configsrr9rIrZr[rrHrSr2r3r4 __classcell__)rWr%s@@r&rErEnsk" H%J%':;Mz86K 59M59N26K ##$((qr)rEN)rEr7r )huggingface_hub.dataclassesrconfiguration_utilsrmodels.auto.modeling_autorutilsrrautorr get_loggerr+rLr r7rE__all__r*r)r&rgs,/3J,-   H %?@$4AB?@%$%5%$A%$P?@N(.N(AN(b ir)