AdapterFusion Adapters
Collection
Adapters from the paper "AdapterFusion: Non-Destructive Task Composition for Transfer Learning" (Pfeiffer et al., 2021)
•
28 items
•
Updated
•
1
bert-base-uncased-cosmosqa_pfeiffer
for bert-base-uncased
Pfeiffer Adapter trained on Cosmos QA.
This adapter was created for usage with the Adapters library.
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("bert-base-uncased")
adapter_name = model.load_adapter("AdapterHub/bert-base-uncased-cosmosqa_pfeiffer")
model.set_active_adapters(adapter_name)
@article{Pfeiffer2020AdapterFusion,
author = {Pfeiffer, Jonas and Kamath, Aishwarya and R{\"{u}}ckl{\'{e}}, Andreas and Cho, Kyunghyun and Gurevych, Iryna},
journal = {arXiv preprint},
title = {{AdapterFusion}: Non-Destructive Task Composition for Transfer Learning},
url = {https://arxiv.org/pdf/2005.00247.pdf},
year = {2020}
}
This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/ukp/bert-base-uncased-cosmosqa_pfeiffer.yaml.