pyvene.models.gru.modelings_intervenable_gru

pyvene.models.gru.modelings_intervenable_gru#

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

gru_type_to_dimension_mapping

mlp model with classification head

gru_classifier_type_to_dimension_mapping

mlp model with lm head

Functions

create_gru(config[, tokenizer_name, cache_dir])

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

create_gru_classifier(config[, ...])

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

create_gru_lm(config[, tokenizer_name, ...])

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