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

Task Adapters

Pre-trained model:

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

WinoGrande

WinoGrande is a new collection of 44k problems, inspired by Winograd Schema Challenge (Levesque, Davis, and Morgenstern 2011), but adjusted to improve the scale and robustness against the dataset-specific bias.
  Website 🤗  huggingface.co
comsense/winogrande@ukp bert-base-uncased
1 version Architecture: pfeiffer Head: 

Pfeiffer Adapter trained on the WinoGrande dataset.

comsense/winogrande@ukp roberta-base
1 version Architecture: pfeiffer Head: 

Pfeiffer Adapter trained on the WinoGrande dataset.

AdapterHub/bert-base-uncased-pf-winogrande bert-base-uncased
huggingface.co Head: 

# Adapter `AdapterHub/bert-base-uncased-pf-winogrande` for bert-base-uncased An [adapter](https://adapterhub.ml) for the `bert-base-uncased` model that was trained on the...

AdapterHub/roberta-base-pf-winogrande roberta-base
huggingface.co Head: 

# Adapter `AdapterHub/roberta-base-pf-winogrande` for roberta-base An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the...

Paper | Imprint & Privacy

Brought to you with ❤️  by authors from: