Downloads · 30 days
12
13% of all-time downloads
AdapterHub/bert-base-multilingual-cased_wikiann_ner_ja_pfeiffer
bert-base-multilingual-cased_wikiann_ner_ja_pfeiffer is a token classification model from AdapterHub. Use it when you need labels on individual words, such as names. It is set up for adapter-transformers. The card lists the license as apache-2.0.
Stacked adapter on top of Language adapter. MAD-X 2.0 style. The language adapters in the last layer (layer 11) are deleted.
Downloads · 30 days
12
13% of all-time downloads
All-time downloads
95
Public
Repo size
16.6 MB
Likes
0
Public
Click a slice to open those files.
.bin3.3 MB · 100%
From the Hugging Face model README
bert-base-multilingual-cased_wikiann_ner_ja_pfeiffer for bert-base-multilingual-casedStacked adapter on top of Language adapter. MAD-X 2.0 style. The language adapters in the last layer (layer 11) are deleted.
This adapter was created for usage with the Adapters library.
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-multilingual-cased")
adapter_name = model.load_adapter("AdapterHub/bert-base-multilingual-cased_wikiann_ner_ja_pfeiffer")
model.set_active_adapters(adapter_name)
1 (main)2345@article{Pfeiffer21UNKs,
author = {Jonas Pfeiffer and
Ivan Vuli\'{c} and
Iryna Gurevych and
Sebastian Ruder},
title = {{UNKs Everywhere: Adapting Multilingual Language Models to New Scripts}},
journal = {arXiv preprint},
year = {2021} ,
url = {https://arxiv.org/abs/2012.15562}
}
This adapter has been auto-imported from https://github.com/Adapter-Hub/Hub/blob/master/adapters/ukp/bert-base-multilingual-cased_wikiann_ner_ja_pfeiffer.yaml.