Edit on GitHub

model = AutoAdapterModel.from_pretrained("xlm-roberta-large")
config = AdapterConfig.load("pfeiffer", non_linearity="relu", reduction_factor=2)
model.load_adapter("tk/wiki@ukp", config=config)

Description

Pfeiffer Adapter trained with Masked Language Modelling on Turkmen Wikipedia Articles for 50k steps and a batch size of 64.

Properties

Pre-trained model
xlm-roberta-large
Adapter type
Prediction Head
  No
Task
Turkmen
Dataset

Architecture

Name
pfeiffer
Non-linearity
relu
Reduction factor
2
{
  "ln_after": false,
  "ln_before": false,
  "mh_adapter": false,
  "output_adapter": true,
  "adapter_residual_before_ln": false,
  "non_linearity": "relu",
  "original_ln_after": true,
  "original_ln_before": true,
  "reduction_factor": 2,
  "residual_before_ln": true
}

Author

  Name
Jonas Pfeiffer
  GitHub
  Twitter

Versions

Identifier Comment Score Download
madx DEFAULT

Citations

Adapter
@article{pfeiffer20madx,
  title={{MAD-X}: An {A}dapter-based {F}ramework for {M}ulti-task {C}ross-lingual {T}ransfer},
  author={Pfeiffer, Jonas and Vuli\'{c}, Ivan and Gurevych, Iryna and Ruder, Sebastian},
  journal={arXiv preprint},
  year={2020},
  url={https://arxiv.org/pdf/2005.00052.pdf},
}
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}
}