README.md

metadata

tags:
  - autotrain
  - token-classification
  - arxiv:2104.09617
  - mlx
base_model: NbAiLab/nb-bert-base
datasets:
  - ltgoslo/norne
license: apache-2.0
language:
  - 'no'
  - nb
  - nn
pipeline_tag: token-classification
library_name: transformers
inference:
  parameters:
    aggregation_strategy: first
widget:
  - text: >-
      Trond Giske har bekreftet på spørsmål fra Adresseavisen at Hansen leide et
      rom i hans leilighet i Trondheim.
model-index:
  - name: NbAiLab/nb-bert-base-pos
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: ltgoslo/norne
          type: ltgoslo/norne
          args: bokmaal
        metrics:
          - name: Test Loss
            type: loss
            value: 0.0650700181722641
          - name: Test Precision
            type: precision
            value: 0.985085078075765
          - name: Test Recall
            type: recall
            value: 0.9877826148012919
          - name: Test F1
            type: f1
            value: 0.9864320022438031
          - name: Test Accuracy
            type: accuracy
            value: 0.9861949007001629
metrics:
  - accuracy
  - f1
  - precision
  - recall

Release 1.0 (November 6, 2024)

nb-bert-base-pos

Description

NB-Bert base model fine-tuned on the Part of Speech task using the NorNE dataset.

Usage

from transformers import pipeline

pos = pipeline("token-classification", "NbAiLab/nb-bert-base-pos")
example = "Jeg heter Kjell og bor i Oslo."

pos_results = pos(example)
print(ner_results)

More on https://arxiv.org/abs/2104.09617