Batteryscibert Uncased Abstract

🚀 BatterySciBERT-uncased for Battery Abstract Classification

BatterySciBERT-uncased is a pre - trained language model designed for battery abstract classification, offering high - performance text classification capabilities.

🚀 Quick Start

This section provides an overview of the BatterySciBERT - uncased model for battery abstract classification, including its basic information, hyperparameters, performance, usage, authors, and citation details.

✨ Features

• Language Model: batteryscibert - uncased
• Language: English
• Downstream - task: Text Classification
• Training data: training_data.csv
• Eval data: val_data.csv
• Code: See example
• Infrastructure: 8x DGX A100

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
model_name = "batterydata/batteryscibert-uncased-abstract"

# a) Get predictions
nlp = pipeline('text-classification', model=model_name, tokenizer=model_name)
input = {'The typical non-aqueous electrolyte for commercial Li-ion cells is a solution of LiPF6 in linear and cyclic carbonates.'}
res = nlp(input)

# b) Load model & tokenizer
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

🔧 Technical Details

Hyperparameters

batch_size = 32
n_epochs = 14
base_LM_model = "batteryscibert-uncased"
learning_rate = 2e-5

Performance

"Validation accuracy": 97.12,
"Test accuracy": 97.47,

📄 License

This project is licensed under the Apache 2.0 license.

👥 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