Edit model card

Electra base model for QA (SQuAD 2.0)

This model uses electra-base.

Training Data

The models have been trained on the SQuAD 2.0 dataset.

It can be used for question answering task.

Usage and Performance

The trained model can be used like this:

from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

# Load model & tokenizer
electra_model = AutoModelForQuestionAnswering.from_pretrained('navteca/electra-base-squad2')
electra_tokenizer = AutoTokenizer.from_pretrained('navteca/electra-base-squad2')

# Get predictions
nlp = pipeline('question-answering', model=electra_model, tokenizer=electra_tokenizer)

result = nlp({
    'question': 'How many people live in Berlin?',
    'context': 'Berlin had a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.'


#  "answer": "3,520,031"
#  "end": 36,
#  "score": 0.99983448,
#  "start": 27,
Downloads last month
Hosted inference API
Question Answering
This model can be loaded on the Inference API on-demand.

Dataset used to train navteca/electra-base-squad2