AdapterHub
  •   Explore
  •   Docs
  •   Blog
  •  
  •  
  1. Explore
  2. Task

Task Adapters

Pre-trained model:

All architectures
All architectures
bert xlm-roberta distilbert gpt2 bart roberta mbart

English

NER on Wikipedia Documents.
wikiann/en@ukp bert-base-multilingual-cased
6 versions Architecture: pfeiffer non-linearity: gelu reduction factor: 16 Head: 

Stacked adapter on top of Language adapter. MAD-X 2.0 style. The language adapters in the last layer (layer 11) are deleted.

Paper

Brought to you with ❤️ by the AdapterHub Team