BERT-base uncased model fine-tuned on SQuAD v1

This model is block-sparse.

That means that with the right runtime it can run roughly 3x faster than an dense network, with 25% of the original weights.

This of course has some impact on the accuracy (see below).

It uses a modified version of Victor Sanh Movement Pruning method.

This model was fine-tuned from the HuggingFace BERT base uncased checkpoint on SQuAD1.1. This model is case-insensitive: it does not make a difference between english and English.


Dataset Split # samples
SQuAD1.1 train 90.6K
SQuAD1.1 eval 11.1k


  • Python: 3.8.5

  • Machine specs:

    CPU: Intel(R) Core(TM) i7-6700K CPU

    Memory: 64 GiB

    GPUs: 1 GeForce GTX 3090, with 24GiB memory

    GPU driver: 455.23.05, CUDA: 11.1


Model size: 418M

Metric # Value # Original (Table 2)
EM 74.82 80.8
F1 83.7 88.5

Note that the above results didn't involve any hyperparameter search.

Example Usage

from transformers import pipeline

qa_pipeline = pipeline(

predictions = qa_pipeline({
    'context': "Frédéric François Chopin, born Fryderyk Franciszek Chopin (1 March 1810 – 17 October 1849), was a Polish composer and virtuoso pianist of the Romantic era who wrote primarily for solo piano.",
    'question': "Who is Frederic Chopin?",


Select AutoNLP in the “Train” menu to fine-tune this model automatically.

Downloads last month
Hosted inference API
Question Answering
This model can be loaded on the Inference API on-demand.