wlsgusjjn/MedNTDs

📦 Model Artifacts

The quantized deployment artifacts for MedNTDs are publicly available.

We provide optimized formats for edge and cross-platform inference:

• GGUF (llama.cpp compatible) – for high-performance CPU inference
• TFLite (.task) – for mobile and embedded deployment

🔗 Hugging Face Repository

Model files are hosted on Hugging Face:
👉 https://huggingface.co/wlsgusjjn/MedNTDs

🔗 GitHub Repository

Full training pipeline, quantization scripts, and deployment code:
👉 https://github.com/wlsgusjjn/MedNTDs/

These artifacts include:

• 4-bit quantized GGUF models for offline edge inference
• LiteRT / TFLite task models for Flutter-based mobile integration
• LoRA-adapted MedGemma checkpoints used in the 2-stage screening pipeline

All models are optimized for low-resource environments and designed for internet-independent deployment in rural clinical settings.