Back to all models
question-answering mask_token:
Query this model
🔥 This model is currently loaded and running on the Inference API. ⚠️ This model could not be loaded by the inference API. ⚠️ This model can be loaded on the Inference API on-demand.
JSON Output
API endpoint  

⚡️ Upgrade your account to access the Inference API

Share Copied link to clipboard

Monthly model downloads

mrm8488/mobilebert-uncased-finetuned-squadv2 mrm8488/mobilebert-uncased-finetuned-squadv2
last 30 days



Contributed by

mrm8488 Manuel Romero
155 models

How to use this model directly from the 🤗/transformers library:

Copy to clipboard
from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("mrm8488/mobilebert-uncased-finetuned-squadv2") model = AutoModelForQuestionAnswering.from_pretrained("mrm8488/mobilebert-uncased-finetuned-squadv2")

MobileBERT + SQuAD v2 📱❓

mobilebert-uncased fine-tuned on SQUAD v2.0 dataset for Q&A downstream task.

Details of the downstream task (Q&A) - Model 🧠

MobileBERT is a thin version of BERT_LARGE, while equipped with bottleneck structures and a carefully designed balance between self-attentions and feed-forward networks.

The checkpoint used here is the original MobileBert Optimized Uncased English: (uncased_L-24_H-128_B-512_A-4_F-4_OPT) checkpoint.

More about the model here

Details of the downstream task (Q&A) - Dataset 📚

SQuAD2.0 combines the 100,000 questions in SQuAD1.1 with over 50,000 unanswerable questions written adversarially by crowdworkers to look similar to answerable ones. To do well on SQuAD2.0, systems must not only answer questions when possible, but also determine when no answer is supported by the paragraph and abstain from answering.

Model training 🏋️‍

The model was trained on a Tesla P100 GPU and 25GB of RAM with the following command:

python transformers/examples/question-answering/ \
  --model_type bert \
  --model_name_or_path 'google/mobilebert-uncased' \
  --do_eval \
  --do_train \
  --do_lower_case \
  --train_file '/content/dataset/train-v2.0.json' \
  --predict_file '/content/dataset/dev-v2.0.json' \
  --per_gpu_train_batch_size 16 \
  --learning_rate 3e-5 \
  --num_train_epochs 5 \
  --max_seq_length 384 \
  --doc_stride 128 \
  --output_dir '/content/output' \
  --overwrite_output_dir \
  --save_steps 1000 \

It is importatnt to say that this models converges much faster than other ones. So, it is also cheap to fine-tune.

Test set Results 🧾

Metric # Value
EM 75.37
F1 78.48
Size 94 MB

Model in action 🚀

Fast usage with pipelines:

from transformers import pipeline
QnA_pipeline = pipeline('question-answering', model='mrm8488/mobilebert-uncased-finetuned-squadv2')
    'context': 'A new strain of flu that has the potential to become a pandemic has been identified in China by scientists.',
    'question': 'Who did identified it ?'

# Output: {'answer': 'scientists.', 'end': 106, 'score': 0.41531604528427124, 'start': 96}

Created by Manuel Romero/@mrm8488 | LinkedIn

Made with in Spain