tags: | |
- adapter-transformers | |
- text-classification | |
- adapterhub:lingaccept/cola | |
- bart | |
license: "apache-2.0" | |
# Adapter `facebook-bart-base_lingaccept_cola_pfeiffer` for facebook/bart-base | |
Adapter for bart-base in Pfeiffer architecture trained on the CoLA dataset for 15 epochs with early stopping and a learning rate of 1e-4. | |
**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("facebook/bart-base") | |
adapter_name = model.load_adapter("AdapterHub/facebook-bart-base_lingaccept_cola_pfeiffer") | |
model.set_active_adapters(adapter_name) | |
``` | |
## Architecture & Training | |
- Adapter architecture: pfeiffer | |
- Prediction head: classification | |
- Dataset: [CoLA](https://nyu-mll.github.io/CoLA/) | |
## Author Information | |
- Author name(s): Clifton Poth | |
- Author email: calpt@mail.de | |
- Author links: [Website](https://calpt.github.io), [GitHub](https://github.com/calpt), [Twitter](https://twitter.com/@clifapt) | |
## Citation | |
```bibtex | |
``` | |
*This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/ukp/facebook-bart-base_lingaccept_cola_pfeiffer.yaml*. |