BERT BASE (cased) finetuned on Bulgarian named-entity-recognition data

Pretrained model on Bulgarian language using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is cased: it does make a difference between bulgarian and Bulgarian. The training data is Bulgarian text from OSCAR, Chitanka and Wikipedia.

It was finetuned on public named-entity-recognition Bulgarian data.

Then, it was compressed via progressive module replacing.

How to use

Here is how to use this model in PyTorch:

>>> from transformers import pipeline
>>> 
>>> model = pipeline(
>>>     'ner',
>>>     model='rmihaylov/bert-base-ner-theseus-bg',
>>>     tokenizer='rmihaylov/bert-base-ner-theseus-bg',
>>>     device=0,
>>>     revision=None)
>>> output = model('Здравей, аз се казвам Иван.')
>>> print(output)

[{'end': 26,
  'entity': 'B-PER',
  'index': 6,
  'score': 0.9937722,
  'start': 21,
  'word': '▁Иван'}]