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

Task Adapters

Pre-trained model:

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

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 roberta-large
1 version Architecture: pfeiffer Head: 

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

sentiment/sst-2@ukp roberta-large
1 version Architecture: houlsby Head: 

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

Paper

Brought to you with ❤️ by the AdapterHub Team