Mobilebert Uncased Finetuned Squadv1

🚀 MobileBERT + SQuAD (v1.1) 📱❓

This project features the mobilebert-uncased model fine - tuned on the SQUAD v2.0 dataset for the Question & Answer downstream task. It offers an efficient solution for Q&A scenarios.

✨ Features

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

MobileBERT is a streamlined version of BERT_LARGE. It is equipped with bottleneck structures and a well - 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. For more information about the model, refer to here.

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

The Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset. It consists of questions posed by crowdworkers on a set of Wikipedia articles. The answer to each question is a text segment, or span, from the corresponding reading passage, or the question might be unanswerable. SQuAD v1.1 contains 100,000+ question - answer pairs on 500+ articles.

📦 Installation

🏋️‍ Model training

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

python transformers/examples/question-answering/run_squad.py \
  --model_type bert \
  --model_name_or_path 'google/mobilebert-uncased' \
  --do_eval \
  --do_train \
  --do_lower_case \
  --train_file '/content/dataset/train-v1.1.json' \
  --predict_file '/content/dataset/dev-v1.1.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's worth noting that this model converges much faster than others, making fine - tuning cost - effective.

📚 Documentation

🧾 Test set Results

💻 Usage Examples

🚀 Model in action

Fast usage with pipelines:

from transformers import pipeline
QnA_pipeline = pipeline('question-answering', model='mrm8488/mobilebert-uncased-finetuned-squadv1')
QnA_pipeline({
    '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': 0.7885545492172241, 'start': 96}

Created by Manuel Romero/@mrm8488 | LinkedIn

Made with ♥ in Spain