fin-mpnet-v1

fin-mpnet-v1

A fine-tuned financial embeddings model based on sentence-transformers/all-mpnet-base-v2.

Model Description

This model has been fine-tuned on financial documents to provide better embeddings for financial text understanding and similarity tasks.

Base Model

• Architecture: sentence-transformers/all-mpnet-base-v2

Training Data

The model was trained on a diverse dataset of financial documents including:

• Stock market reports
• Financial glossaries
• Mutual fund documentation
• Equity research reports
• Financial and derivatives documentation

Usage

Basic Usage

from sentence_transformers import SentenceTransformer, util

# Load the model (assuming it's already loaded in a previous cell)
model_name = 'sentence-transformers/all-mpnet-base-v2'
model = SentenceTransformer(model_name)

test_pairs = [
    ("valuation", "price to earnings ratio"),
    ("valuation", "earnings per share")
]

# Calculate and print similarity scores for each pair
print("Cosine similarity scores for test pairs:")
for sentence1, sentence2 in test_pairs:
    embedding1 = model.encode(sentence1, convert_to_tensor=True)
    embedding2 = model.encode(sentence2, convert_to_tensor=True)
    cosine_score = util.cos_sim(embedding1, embedding2)
    print(f"'{sentence1}' vs '{sentence2}': {cosine_score[0][0].item():.4f}")

Model Performance

This model has been optimized for financial text understanding tasks including:

• Financial document similarity
• Term definition matching
• Context-aware financial embeddings
• Risk assessment text analysis

Comparison table

Technical Details

• Model Type: Transformer-based encoder
• Hidden Size: 768
• Max Sequence Length: 512 tokens
• Embedding Dimension: 768

Citation

If you use this model in your research, please cite:

@misc{finance-embeddings-2025,
  title={Finance Embeddings: A Specialized Model for Financial Text Understanding},
  author={Finance Embeddings Team},
  year={2025},
  howpublished={\url{https://huggingface.co/finance-embeddings-mpnet-v1}}
}

License

This model follows the same license as the base model: sentence-transformers/all-mpnet-base-v2

Contact

For questions about this model, please open an issue in the repository.