pyvene.models.blip.modelings_intervenable_blip

Each modeling file in this library is a mapping between abstract naming of intervention anchor points and actual model module defined in the huggingface library.

We also want to let the intervention library know how to config the dimensions of intervention based on model config defined in the huggingface library.

Module Attributes

blip_type_to_dimension_mapping

blip model with wrapper

Functions

create_blip([name, cache_dir])

Creates a BLIP VQA model, config, and tokenizer from the given name and revision