This is the final, fully aligned (Phase 3) LoRA adapter for the Cardiology expert. While Phase 1 taught the model cardiology science and Phase 2 taught it to chat, Phase 3 utilizes Direct Preference Optimization (DPO) to align the model's outputs for structural safety, factual adherence, and proper clinical formatting.

Developed by: Hriday75
Model type: LoRA Adapter (PEFT)
Language: English
Finetuned from base model: unsloth/Qwen2.5-3B-bnb-4bit (via Phase 2 Cardiology Chat LoRA)
Training Stage: Phase 3 (Direct Preference Optimization - DPO)

Uses

This model is intended to be used in high-fidelity clinical routing pipelines where structural output constraints are just as important as clinical accuracy. It is designed to heavily penalize hallucinated reasoning paths or structurally invalid medical data formatting.

Training Details

Training Data

This adapter was aligned using the ai-galileo/clinical-notes-to-fhir dataset. This dataset acts as a preference learning corpus, providing the model with chosen (structurally valid medical outputs) and rejected (annotated structural or formatting errors) examples to learn from.

Training Procedure

Trained using unsloth and the TRL DPOTrainer. DPO requires an extremely low learning rate to subtly shift the model's generation probabilities toward the "chosen" format without destroying the scientific knowledge learned in Phases 1 and 2.

How to Get Started with the Model

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

# 1. Load the base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-3B-bnb-4bit")
tokenizer = AutoTokenizer.from_pretrained("unsloth/Qwen2.5-3B-bnb-4bit")

# 2. Attach this DPO Aligned Cardiology Adapter
model = PeftModel.from_pretrained(base_model, "Hriday75/qwen2.5-3b-cardio-dpo-aligned")

# 3. Format your chat prompt
messages = [
    {"role": "system", "content": "You are a helpful, empathetic cardiology expert."},
    {"role": "user", "content": "Please format the patient's recent Holter monitor results into a structured summary."}
]

inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt"
)