mobilebert-uncased-squad-v2

  # after install https://github.com/huggingface/transformers

  cd examples/question-answering
  mkdir -p data

  wget -O data/train-v2.0.json https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v2.0.json

  wget -O data/dev-v2.0.json  https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v2.0.json

  export SQUAD_DIR=`pwd`/data

  python run_squad.py \
    --model_type mobilebert \
    --model_name_or_path google/mobilebert-uncased \
    --do_train \
    --do_eval \
    --do_lower_case \
    --version_2_with_negative \
    --train_file $SQUAD_DIR/train-v2.0.json \
    --predict_file $SQUAD_DIR/dev-v2.0.json \
    --per_gpu_train_batch_size 16 \
    --per_gpu_eval_batch_size 16 \
    --learning_rate 4e-5 \
    --num_train_epochs 5.0 \
    --max_seq_length 320 \
    --doc_stride 128 \
    --warmup_steps 1400 \
    --save_steps 2000 \
    --output_dir $SQUAD_DIR/mobilebert-uncased-warmup-squad_v2 2>&1 | tee train-mobilebert-warmup-squad_v2.log

from transformers import pipeline

qa_pipeline = pipeline(
    "question-answering",
    model="csarron/mobilebert-uncased-squad-v2",
    tokenizer="csarron/mobilebert-uncased-squad-v2"
)

predictions = qa_pipeline({
    'context': "The game was played on February 7, 2016 at Levi's Stadium in the San Francisco Bay Area at Santa Clara, California.",
    'question': "What day was the game played on?"
})

print(predictions)
# output:
# {'score': 0.71434086561203, 'start': 23, 'end': 39, 'answer': 'February 7, 2016'}