medical-gemma-270m-mlx

Medical-Gemma3-270M (Adapter Only)

This repository contains an ultra-portable LoRA Adapter (15 MB) for Gemma-3-270m-it, fine-tuned natively on Apple Silicon for clinical dialogue-to-SOAP-note summarization.

🚀 The Efficiency Advantage

With a tiny 15 MB footprint, this Adapter-only release is optimized for high-speed inference on edge devices, mobile hardware, and local workstations. It acts as a lightweight "medical brain patch" for the foundational Gemma-3-270m-it model.

🎯 Performance Gain

• ROUGE-L Improvement: +64.4% gain over the base 270M model.
• Optimal Use Case: Extreme speed and low-memory clinical documentation for embedded and mobile applications.

🌍 Cross-Platform Support

While trained with MLX, these adapters are architecture-agnostic:

• Linux/Windows: Use Hugging Face transformers + PEFT.
• Edge/CPU: Convert to GGUF (llama.cpp) for use on mobile and local CPUs.

📂 Training & Evaluation

• Training Dataset: MedSynth (Synthetic Medical Dialogue-Note Pairs).
• Evaluation Dataset: MTS-Dialog (Real clinical dialogues from the Task 1 benchmark).

⚖️ Licensing

• MTS-Dialog: CC BY 4.0 (Commercial use allowed with attribution).
• MedSynth: No explicit license mentioned; intended for research purposes.
• Base Model: Google Gemma License (Permissive).

🛠 Usage (MLX)

To test the model immediately, run the included inference script:

python3 run_inference.py "Patient: My throat has been sore. Doctor: Any cough? Patient: No cough."

📜 Ethical Disclaimer

This model is for research purposes only and is not a clinical diagnostic tool.