CardioEmbed-Qwen3-8B

A LoRA fine-tuned version of Qwen/Qwen3-Embedding-8B optimized for cardiology and medical text embeddings.

Model Details

• Base Model: Qwen/Qwen3-Embedding-8B
• Fine-tuning Method: LoRA (Low-Rank Adaptation)
• Domain: Medical/Cardiology
• Task: Text Embeddings / Semantic Similarity

Part of the CardioEmbed Series

This model is part of the CardioEmbed series, which includes embeddings models of various sizes optimized for cardiology text:

• CardioEmbed
• CardioEmbed-BGE-M3
• CardioEmbed-Qwen3-4B
• CardioEmbed-Qwen3-8B (this model)
• And more...

Usage

from peft import PeftModel
from transformers import AutoModel, AutoTokenizer

base_model = AutoModel.from_pretrained("Qwen/Qwen3-Embedding-8B")
model = PeftModel.from_pretrained(base_model, "richardyoung/CardioEmbed-Qwen3-8B")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-Embedding-8B")

text = "Patient presents with chest pain and shortness of breath"
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
outputs = model(**inputs)
embeddings = outputs.last_hidden_state.mean(dim=1)

Use Cases

• Medical document retrieval
• Clinical note similarity
• Cardiology literature search
• Patient case matching

Credits

• Model Curator: Richard Young | DeepNeuro.AI
• Base Model: Qwen Team