Edit on GitHub

model = AutoAdapterModel.from_pretrained("bert-base-uncased")
config = AdapterConfig.load("houlsby")
model.load_adapter("sts/mrpc@ukp", config=config)

Description

Adapter in Houlsby architecture trained on the MRPC task for 20 epochs with early stopping and a learning rate of 1e-4. See https://arxiv.org/pdf/2007.07779.pdf.

Properties

Pre-trained model
bert-base-uncased
Adapter type
Prediction Head
  Yes
Task
Semantic Textual Similarity
Dataset

Architecture

Name
houlsby
Non-linearity
swish
Reduction factor
16
{
  "ln_after": false,
  "ln_before": false,
  "mh_adapter": true,
  "output_adapter": true,
  "adapter_residual_before_ln": false,
  "non_linearity": null,
  "original_ln_after": true,
  "original_ln_before": false,
  "reduction_factor": null,
  "residual_before_ln": true
}

Author

  Name
Clifton Poth
  GitHub
  Twitter

Versions

Identifier Comment Score Download
1 DEFAULT

Citations

Adapter
@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}
}
Architecture
@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}
}
Task
@inproceedings{Dolan2005AutomaticallyCA,
  title={Automatically Constructing a Corpus of Sentential Paraphrases},
  author={William B. Dolan and Chris Brockett},
  booktitle={IWP@IJCNLP},
  year={2005}
}