Task Adapters

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-base

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).

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).

sentiment/sst-2@ukp roberta-base

1 version Architecture: pfeiffer Head:

Pfeiffer Adapter trained on the SST-2 task.

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).

AdapterHub/roberta-base-pf-sst2 roberta-base

huggingface.co Head:

# Adapter `AdapterHub/roberta-base-pf-sst2` for roberta-base An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the...