calpt's picture
Add adapter bert-base-uncased_qa_squad1_houlsby version 1
030ec68 verified
metadata
tags:
  - bert
  - question-answering
  - adapter-transformers
  - adapterhub:qa/squad1
datasets:
  - squad
license: apache-2.0

Adapter bert-base-uncased_qa_squad1_houlsby for bert-base-uncased

Adapter for bert-base in Houlsby architecture trained on the SQuAD 1.1 dataset for 15 epochs with early stopping and a learning rate of 3e-4.

This adapter was created for usage with the Adapters library.

Usage

First, install adapters:

pip install -U adapters

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

from adapters import AutoAdapterModel

model = AutoAdapterModel.from_pretrained("bert-base-uncased")
adapter_name = model.load_adapter("AdapterHub/bert-base-uncased_qa_squad1_houlsby")
model.set_active_adapters(adapter_name)

Architecture & Training

  • Adapter architecture: houlsby
  • Prediction head: question answering
  • Dataset: SQuAD 1.1

Author Information

Citation


This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/ukp/bert-base-uncased_qa_squad1_houlsby.yaml.