CoolFace
Modelpublic

richardyoung/CardioEmbed-BGE-M3

sourceHugging Faceapache-2.0updated 10mo agoView on Hugging Face
0likes6downloads
Model Card

CardioEmbed-BGE-M3

Domain-specialized cardiology text embeddings using LoRA-adapted BGE-M3

Part of a comparative study of 10 embedding architectures for clinical cardiology.

Performance

MetricScore
Separation Score0.209

Usage

python
from transformers import AutoModel, AutoTokenizer
from peft import PeftModel

base_model = AutoModel.from_pretrained("BAAI/bge-m3")
tokenizer = AutoTokenizer.from_pretrained("BAAI/bge-m3")
model = PeftModel.from_pretrained(base_model, "richardyoung/CardioEmbed-BGE-M3")

Training

  • —Training Data: 106,535 cardiology text pairs from medical textbooks
  • —Method: LoRA fine-tuning (r=16, alpha=32)
  • —Loss: Multiple Negatives Ranking Loss (InfoNCE)

Citation

bibtex
@article{young2024comparative,
  title={Comparative Analysis of LoRA-Adapted Embedding Models for Clinical Cardiology Text Representation},
  author={Young, Richard J and Matthews, Alice M},
  journal={arXiv preprint},
  year={2024}
}