+ j(Rt^RIHt^RIHt^RIHtHtHtH t H t ^RI H t H t Ht^RIHt]P"!]4t] !RR]44tR.tR#) zq Processor class for InstructBLIP. Largely copy of Blip2Processor with addition of a tokenizer for the Q-Former. ) BatchFeature)ProcessorMixin) AddedTokenPaddingStrategyPreTokenizedInput TextInputTruncationStrategy) TensorTypeauto_docstringlogging) VideoInputcfaa]tRt^"toRV3Rllt]RV3RlRll4t]R4tRt Vt V;t #)InstructBlipVideoProcessorc <\VR4'g3\RRRR7VnVPVP.RR7MVPVnW@n\ SV`WV4R#)z qformer_tokenizer (`AutoTokenizer`): An instance of ['PreTrainedTokenizer`]. The Q-Former tokenizer is a required input. num_query_tokens (`int`, *optional*): Number of tokens used by the Qformer as queries, should be same as in model's config. video_tokenz