Adapter bert-base-uncased_nli_rte_houlsby
for bert-base-uncased
Adapter in Houlsby architecture trained on the RTE task for 20 epochs with early stopping and a learning rate of 1e-4. See https://arxiv.org/pdf/2007.07779.pdf.
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("bert-base-uncased")
adapter_name = model.load_adapter("AdapterHub/bert-base-uncased_nli_rte_houlsby")
model.set_active_adapters(adapter_name)
Architecture & Training
- Adapter architecture: houlsby
- Prediction head: classification
- Dataset: RTE
Author Information
- Author name(s): Clifton Poth
- Author email: calpt@mail.de
- Author links: Website, GitHub, Twitter
Citation
@article{pfeiffer2020AdapterHub,
title={AdapterHub: A Framework for Adapting Transformers},
author={Jonas Pfeiffer and
Andreas R\"uckl\'{e} and
Clifton Poth and
Aishwarya Kamath and
Ivan Vuli\'{c} and
Sebastian Ruder and
Kyunghyun Cho and
Iryna Gurevych},
journal={arXiv preprint},
year={2020},
url={https://arxiv.org/abs/2007.07779}
}
This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/ukp/bert-base-uncased_nli_rte_houlsby.yaml.
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.