View on huggingface.co 

model = AutoAdapterModel.from_pretrained("facebook/bart-base")
model.load_adapter("AdapterHub/narrativeqa", source="hf")

Description

Adapter hSterz/narrativeqa for facebook/bart-base

An adapter for the facebook/bart-base model that was trained on the qa/narrativeqa dataset.

This adapter was created for usage with the adapter-transformers library.

Usage

First, install adapter-transformers:

pip install -U adapter-transformers

Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. More

Now, the adapter can be loaded and activated like this:

from transformers import AutoModelWithHeads

model = AutoModelWithHeads.from_pretrained("facebook/bart-base")
adapter_name = model.load_adapter("hSterz/narrativeqa", source="hf", set_active=True)

Architecture & Training

Evaluation results

Citation

Properties

Pre-trained model
facebook/bart-base
Adapter type
Task
Prediction Head
  Yes
Task
Question Answering
Dataset
narrativeqa

Architecture

{
  "adapter_residual_before_ln": false,
  "cross_adapter": false,
  "inv_adapter": null,
  "inv_adapter_reduction_factor": null,
  "leave_out": [],
  "ln_after": false,
  "ln_before": false,
  "mh_adapter": false,
  "non_linearity": "relu",
  "original_ln_after": true,
  "original_ln_before": true,
  "output_adapter": true,
  "reduction_factor": 16,
  "residual_before_ln": true
}

Citations

Task
@article{narrativeqa,
author = {Tom\'a\v s Ko\v cisk\'y and Jonathan Schwarz and Phil Blunsom and
          Chris Dyer and Karl Moritz Hermann and G\'abor Melis and
          Edward Grefenstette},
title = {The {NarrativeQA} Reading Comprehension Challenge},
journal = {Transactions of the Association for Computational Linguistics},
url = {https://TBD},
volume = {TBD},
year = {2018},
pages = {TBD},
}