model = AutoAdapterModel.from_pretrained("facebook/bart-large")
config = AdapterConfig.load("houlsby", non_linearity="swish", reduction_factor=2)
model.load_adapter("sum/xsum@ukp", config=config){
"ln_after": false,
"ln_before": false,
"mh_adapter": true,
"output_adapter": true,
"adapter_residual_before_ln": false,
"non_linearity": "swish",
"original_ln_after": true,
"original_ln_before": false,
"reduction_factor": 2,
"residual_before_ln": true
}| Identifier | Comment | Score | Download |
|---|---|---|---|
| 1 DEFAULT | 20.9 |
@misc{houlsby2019parameterefficient,
title={Parameter-Efficient Transfer Learning for NLP},
author={Neil Houlsby and Andrei Giurgiu and Stanislaw Jastrzebski and Bruna Morrone and Quentin de Laroussilhe and Andrea Gesmundo and Mona Attariyan and Sylvain Gelly},
year={2019},
eprint={1902.00751},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
@InProceedings{xsum-emnlp,
author = "Shashi Narayan and Shay B. Cohen and Mirella Lapata",
title = "Don't Give Me the Details, Just the Summary! {T}opic-Aware Convolutional Neural Networks for Extreme Summarization",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing ",
year = "2018",
address = "Brussels, Belgium",
}