README.md

metadata

language:
  - en
thumbnail: url to a thumbnail used in social sharing
tags:
  - token classification
license: cc
datasets:
  - conll2003
model-index:
  - name: sarahmiller137/distilbert-base-uncased-ft-conll2003
    results:
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: conll2003
          type: conll2003
          config: conll2003
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9750189904012154
            verified: true
          - name: Precision
            type: precision
            value: 0.9802152215150602
            verified: true
          - name: Recall
            type: recall
            value: 0.9803021169462076
            verified: true
          - name: F1
            type: f1
            value: 0.9802586673049137
            verified: true
          - name: loss
            type: loss
            value: 0.10723897069692612
            verified: true

Model information:

distilbert-base-uncased model finetuned using the conll2003 dataset from the datasets library.

Intended uses & limitations

This model is intended to be used for named entity recoginition tasks. The model will identify entities of persons, locations, organisations, and miscellaneous. The model will predict lables based upon the CoNLL-2003 dataset.

Note that the dataset and model may not be fully represetative or suitable for all needs it is recommended that the paper for the dataset and base model card should be reviewed before using the model -

• CoNLL-2003
• distilbert

How to use

Load the model from the library using the following checkpoints:

from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("sarahmiller137/distilbert-base-uncased-ft-conll2003")
model = AutoModel.from_pretrained("sarahmiller137/distilbert-base-uncased-ft-conll2003")