Bert Base Cased Squad V1

🚀 BERT-base-cased for QA

This is a BERT-base-cased model specifically designed for question answering tasks, trained on English text and suitable for extractive question answering.

🚀 Quick Start

This model is a BERT-base-cased model used for extractive question answering tasks. It is trained on SQuAD v1 data and can be used for question answering in English. For code examples, please refer to example.

✨ Features

• Language Model: bert-base-cased
• Language: English
• Downstream-task: Extractive QA
• Training data: SQuAD v1
• Eval data: SQuAD v1
• Infrastructure: 8x DGX A100

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

model_name = "batterydata/bert-base-cased-squad-v1"
# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
    'question': 'What is the electrolyte?',
    'context': 'The typical non-aqueous electrolyte for commercial Li-ion cells is a solution of LiPF6 in linear and cyclic carbonates.'
}
res = nlp(QA_input)
# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

Advanced Usage

No advanced usage examples are provided in the original document, so this part is skipped.

📚 Documentation

Hyperparameters

batch_size = 32
n_epochs = 2
base_LM_model = "bert-base-cased"
max_seq_len = 386
learning_rate = 5e-5
doc_stride=128
max_query_length=64

Performance

Evaluated on the SQuAD v1.0 dev set.

"exact": 81.30,
"f1": 88.58,

Evaluated on the battery device dataset.

"precision": 67.02,
"recall": 80.15,

🔧 Technical Details

No specific technical details are provided in the original document, so this section is skipped.

📄 License

This project is licensed under the Apache-2.0 license.

📋 Information Table

👥 Authors

• Shu Huang: sh2009 [at] cam.ac.uk
• Jacqueline Cole: jmc61 [at] cam.ac.uk

📖 Citation

BatteryBERT: A Pre-trained Language Model for Battery Database Enhancement