EphAsad's picture
Update medical_lora/README.md
d557cbf verified
metadata
base_model: sentence-transformers/all-MiniLM-L6-v2
library_name: peft
license: mit
tags:
  - lora
  - peft
  - medical
  - healthcare
  - domain-adaptation
  - sentence-embeddings
language:
  - en

Medical LoRA Adapter for DomainEmbedder-v2.6

Domain-specific LoRA adapter for medical/healthcare text embeddings.

Model Details

Property Value
Base Model sentence-transformers/all-MiniLM-L6-v2
Parent System DomainEmbedder-v2.6
Domain Medical / Healthcare
LoRA Rank 16
LoRA Alpha 32
Target Modules query, value
Trainable Params 147,456 (0.645%)

Training Data

Trained on 40,000 medical text pairs from:

  • MedQA-USMLE
  • MedQuAD
  • PubMedQA
  • Medical Meadow
  • ChatDoctor

Training Configuration

Parameter Value
Epochs 3
Batch Size 32
Learning Rate 2e-4
Loss Contrastive (InfoNCE)
Best Val Loss 0.0026

Usage

This adapter is part of the DomainEmbedder-v2.6 system. It is selected automatically by the RL policy when medical content is detected.

from peft import PeftModel
from transformers import AutoModel

# Load base encoder
base_encoder = AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')

# Apply medical LoRA
medical_model = PeftModel.from_pretrained(base_encoder, 'path/to/medical_lora')

Author

Zain Asad

License

MIT License

Framework Versions

  • PEFT 0.18.1
  • Transformers 4.x
  • PyTorch 2.x