E5 Base Sts En De

🚀 e5-base-sts-en-de

A fine-tuned multilingual model for semantic textual similarity tasks, achieving high performance on German datasets.

🚀 Quick Start

This model is a fine-tuned version of multilingual-e5-base specifically designed for semantic textual similarity tasks.

✨ Features

• Continuously updated to improve performance.
• Fine-tuned on multiple German datasets for better adaptation to the German language.
• Achieves high scores on semantic textual similarity evaluations.

📦 Installation

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

💻 Usage Examples

No code examples are provided in the original document, so this section is skipped.

📚 Documentation

Model Training

The model has been fine-tuned on the German subsets of the following datasets:

• German paraphrase corpus by Philip May
• paws-x
• stsb_multi_mt

The training procedure can be divided into two stages:

• Training on paraphrase datasets with the Multiple Negatives Ranking Loss.
• Training on semantic textual similarity datasets using the Cosine Similarity Loss.

Results

The model achieves the following results:

• 0.920 on stsb's validation subset.
• 0.904 on stsb's test subset.

🔧 Technical Details

The model is based on the multilingual-e5-base architecture and is fine-tuned for semantic textual similarity tasks. The two-stage training process helps the model better capture semantic information in text.

📄 License

This project is licensed under the MIT License.

⚠️ Important Note

The model is being continuously updated.

💡 Usage Tip

The model is fine-tuned on German datasets, which makes it suitable for semantic textual similarity tasks in the German language.