Edit on GitHub 

model = AutoAdapterModel.from_pretrained("roberta-base")
config = AdapterConfig.load("houlsby")
model.load_adapter("lingaccept/cola@ukp", config=config)

Description

Adapter (with head) trained using the `run_glue.py` script with an extension that retains the best checkpoint (out of 30 epochs).

Properties

Pre-trained model
roberta-base
Adapter type
Task
Prediction Head
  Yes
Task
Linguistic Acceptability
Dataset
CoLA

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
Andreas Rücklé
  E-Mail
rueckle@ukp.informatik.tu-darmstadt.de
  Web
http://rueckle.net
  GitHub
arueckle
  Twitter
arueckle

Versions

Identifier Comment Score Download
1 DEFAULT Achieves 60.07 Matthew's corr on the CoLA devset

Citations

Adapter
@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}
}
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
@article{warstadt2018neural,
  title={Neural Network Acceptability Judgments},
  author={Warstadt, Alex and Singh, Amanpreet and Bowman, Samuel R},
  journal={arXiv preprint arXiv:1805.12471},
  year={2018}
}