Loading [MathJax]/extensions/MathZoom.js
  Edit on GitHub 

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

Description

Adapter in Pfeiffer architecture trained on the QQP 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
Task
Prediction Head
  Yes
Task
Semantic Textual Similarity
Dataset
QQP

Architecture

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

Author

  Name
Clifton Poth
  E-Mail
poth@ukp.informatik.tu-darmstadt.de
  Web
https://www.informatik.tu-darmstadt.de/ukp
  GitHub
calpt
  Twitter
clifapt

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{pfeiffer2020adapterfusion,
  title={AdapterFusion: Non-Destructive Task Composition for Transfer Learning},
  author={Jonas Pfeiffer and Aishwarya Kamath and Andreas Rücklé and Kyunghyun Cho and Iryna Gurevych},
  year={2020},
  eprint={2005.00247},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}
Task
@misc{chen2018quora,
  title={Quora question pairs},
  author={Chen, Zihan and Zhang, Hongbo and Zhang, Xiaoji and Zhao, Leqi},
  year={2018},
  publisher={Quora}
}