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

Task Adapters

Pre-trained model:

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

SST-2

The Stanford Sentiment Treebank is a binary single-sentence classification task consisting of sentences extracted from movie reviews with human annotations of their sentiment.
  Website
sentiment/sst-2@ukp gpt2
1 version Architecture: pfeiffer non-linearity: relu reduction factor: 16 Head: 

Adapter for gpt2 in Pfeiffer architecture trained on the SST-2 dataset for 10 epochs with a learning rate of 1e-4.

Paper | Imprint & Privacy

Brought to you with ❤️  by authors from: