Adapter julian-fong/cifar100-adapterplus_config for google/vit-base-patch16-224-in21k

An adapter for the google/vit-base-patch16-224-in21k model that was trained on the cifar100 dataset and includes a prediction head for image classification.

This adapter was created for usage with the Adapters library.

Usage

First, install adapters:

pip install -U adapters

Now, the adapter can be loaded and activated like this:

from adapters import AutoAdapterModel

model = AutoAdapterModel.from_pretrained("google/vit-base-patch16-224-in21k")
adapter_name = model.load_adapter("julian-fong/cifar100-adapterplus_config", set_active=True)

Architecture & Training

Evaluation results

Citation