pyvene.models.gpt2.modelings_intervenable_gpt2#
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
gpt2 model with LM head |
|
gpt2 model with classifier head |
Functions
|
Creates a GPT2 model, config, and tokenizer from the given name and revision |
|
Creates a GPT2ForSequenceClassification, config, and tokenizer from the given name and revision |
|
Creates a GPT2 LM, config, and tokenizer from the given name and revision |