README.md

metadata

language:
  - 'no'
  - nb
  - nn
inference: false
tags:
  - BERT
  - NorBERT
  - Norwegian
  - encoder
license: cc-by-4.0

NorBERT 3 large

The official release of a new generation of NorBERT language models described in paper NorBench — A Benchmark for Norwegian Language Models. Plese read the paper to learn more details about the model.

Other sizes:

• NorBERT 3 xs (15M)
• NorBERT 3 small (40M)
• NorBERT 3 base (123M)
• NorBERT 3 large (323M)

Generative NorT5 siblings:

• NorT5 xs (32M)
• NorT5 small (88M)
• NorT5 base (228M)
• NorT5 large (808M)

Example usage

This model currently needs a custom wrapper from modeling_norbert.py, you should therefore load the model with trust_remote_code=True.

import torch
from transformers import AutoTokenizer, AutoModelForMaskedLM

tokenizer = AutoTokenizer.from_pretrained("ltg/norbert3-large")
model = AutoModelForMaskedLM.from_pretrained("ltg/norbert3-large", trust_remote_code=True)

mask_id = tokenizer.convert_tokens_to_ids("[MASK]")
input_text = tokenizer("Nå ønsker de seg en[MASK] bolig.", return_tensors="pt")
output_p = bert(**input_text)
output_text = torch.where(input_text.input_ids == mask_id, output_p.logits.argmax(-1), input_text.input_ids)

# should output: '[CLS] Nå ønsker de seg en ny bolig.[SEP]'
print(tokenizer.decode(output_text[0].tolist()))

The following classes are currently implemented: AutoModel, AutoModelMaskedLM, AutoModelForSequenceClassification, AutoModelForTokenClassification, AutoModelForQuestionAnswering and AutoModeltForMultipleChoice.

Cite us

@inproceedings{
samuel2023norbench,
title={NorBench -- A Benchmark for Norwegian Language Models},
author={David Samuel and Andrey Kutuzov and Samia Touileb and Erik Velldal and Lilja {\O}vrelid and Egil R{\o}nningstad and Elina Sigdel and Anna Sergeevna Palatkina},
booktitle={The 24rd Nordic Conference on Computational Linguistics},
year={2023},
url={https://openreview.net/forum?id=WgxNONkAbz}
}