Hugging Face's logo

AdapterHub
/
distilbert-base-uncased_comsense_hellaswag_pfeiffer

Multiple Choice
Adapters
adapterhub:comsense/hellaswag
distilbert
Model card Files Community
distilbert-base-uncased_comsense_hellaswag_pfeiffer / README.md
calpt's picture
calpt
Add adapter distilbert-base-uncased_comsense_hellaswag_pfeiffer version 1
f4be759 verified
preview code
|
raw
history blame contribute delete
1.46 kB
metadata
tags:
  - adapter-transformers
  - multiple-choice
  - adapterhub:comsense/hellaswag
  - distilbert
datasets:
  - hellaswag
license: apache-2.0

Adapter distilbert-base-uncased_comsense_hellaswag_pfeiffer for distilbert-base-uncased

Adapter for distilbert-base-uncased in Pfeiffer architecture trained on the Hellaswag dataset for 15 epochs with early stopping and a learning rate of 1e-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("distilbert-base-uncased")
adapter_name = model.load_adapter("AdapterHub/distilbert-base-uncased_comsense_hellaswag_pfeiffer")
model.set_active_adapters(adapter_name)

Architecture & Training

  • Adapter architecture: pfeiffer
  • Prediction head: multiple choice
  • Dataset: HellaSwag

Author Information

Citation

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