Tielectra Small Sentiment

🚀 Sentiment Analysis for Tigrinya with TiELECTRA small

This model is a fine - tuned version of TiELECTRA small on a YouTube comments Sentiment Analysis dataset for Tigrinya, which helps analyze Tigrinya sentiment effectively.

🚀 Quick Start

💻 Usage Examples

Basic Usage

from transformers import pipeline

ti_sent = pipeline("sentiment-analysis", model="fgaim/tielectra-small-sentiment")
ti_sent("ድምጻዊ ኣብርሃም ኣፈወርቂ ንዘልኣለም ህያው ኮይኑ ኣብ ልብና ይነብር")

📚 Documentation

📦 Installation

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

🔧 Technical Details

Hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e - 05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e - 08
• lr_scheduler_type: linear
• num_epochs: 3.0

Results

The model achieves the following results on the evaluation set:

Framework versions

• Transformers 4.10.3
• Pytorch 1.9.0+cu111
• Datasets 1.10.2
• Tokenizers 0.10.1

📄 License

No license information is provided in the original document, so this section is skipped.

📖 Citation

If you use this model in your product or research, please cite as follows:

@article{Fitsum2021TiPLMs,
  author={Fitsum Gaim and Wonsuk Yang and Jong C. Park},
  title={Monolingual Pre-trained Language Models for Tigrinya},
  year=2021,
  publisher= {WiNLP 2021/EMNLP 2021}
}

📚 References

Tela, A., Woubie, A. and Hautamäki, V. 2020.
Transferring Monolingual Model to Low-Resource Language: The Case of Tigrinya.
ArXiv, abs/2006.07698.