Task Adapters

MRPC

Microsoft Research Paraphrase Corpus consists of sentence pairs automatically extracted from online news sources, with human annotations for whether the sentences in the pair are semantically equivalent.

Website

sts/mrpc@ukp roberta-large

1 version Architecture: pfeiffer Head:

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

sts/mrpc@ukp roberta-large

1 version Architecture: houlsby Head:

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

sts/mrpc@ukp roberta-base

1 version Architecture: pfeiffer Head:

Pfeiffer Adapter trained on the MRPC dataset.

sts/mrpc@ukp roberta-base

1 version Architecture: houlsby Head:

MRPC 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-mrpc roberta-base

huggingface.co Head:

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