|
--- |
|
tags: |
|
- text-classification |
|
- adapter-transformers |
|
- roberta |
|
- adapterhub:sts/mrpc |
|
license: "apache-2.0" |
|
--- |
|
|
|
# Adapter `roberta-large-mrpc_pfeiffer` for roberta-large |
|
|
|
MRPC adapter (with head) trained using the `run_glue.py` script with an extension that retains the best checkpoint (out of 30 epochs). |
|
|
|
|
|
**This adapter was created for usage with the [Adapters](https://github.com/Adapter-Hub/adapters) library.** |
|
|
|
## Usage |
|
|
|
First, install `adapters`: |
|
|
|
``` |
|
pip install -U adapters |
|
``` |
|
|
|
Now, the adapter can be loaded and activated like this: |
|
|
|
```python |
|
from adapters import AutoAdapterModel |
|
|
|
model = AutoAdapterModel.from_pretrained("roberta-large") |
|
adapter_name = model.load_adapter("AdapterHub/roberta-large-mrpc_pfeiffer") |
|
model.set_active_adapters(adapter_name) |
|
``` |
|
|
|
## Architecture & Training |
|
|
|
- Adapter architecture: pfeiffer |
|
- Prediction head: classification |
|
- Dataset: [MRPC](https://www.microsoft.com/en-us/download/details.aspx?id=52398) |
|
|
|
## Author Information |
|
|
|
- Author name(s): Andreas Rücklé |
|
- Author email: [email protected] |
|
- Author links: [Website](http://rueckle.net), [GitHub](https://github.com/arueckle), [Twitter](https://twitter.com/@arueckle) |
|
|
|
|
|
|
|
## Citation |
|
|
|
```bibtex |
|
@article{pfeiffer2020AdapterHub, |
|
title={AdapterHub: A Framework for Adapting Transformers}, |
|
author={Jonas Pfeiffer, |
|
Andreas R\"uckl\'{e}, |
|
Clifton Poth, |
|
Aishwarya Kamath, |
|
Ivan Vuli\'{c}, |
|
Sebastian Ruder, |
|
Kyunghyun Cho, |
|
Iryna Gurevych}, |
|
journal={ArXiv}, |
|
year={2020} |
|
} |
|
|
|
``` |
|
|
|
*This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/ukp/roberta-large-mrpc_pfeiffer.yaml*. |
