Commit History
-
fix(chat): resolve Q&A completion trigger, enhance RAG grounding, and add benchmark audit suite
- Fix RAG completion mimicry by reformatting retrieved guidelines from Q&A to neutral grounding blocks - Disentangle sensor telemetry directives from general lifestyle and medication inquiries - Eliminate chat history duplication and strip disclaimer repetition in conversational memory - Add fail-safe fallback to prevent empty disclaimer-only responses - Prioritize foundational ACC/AHA nutritional and pharmacotherapy guidelines - Add comprehensive benchmark accuracy test suite and update project documentation6198e11
-
feat: upgrade to sub-512MB mobile architecture for iOS (Core ML) and Android (LiteRT)
- Upgrade deployment target to iOS and Android mobile devices (>= 8GB RAM) under strict < 512MB ceiling - Implement 1D-Conformer Biosignal Encoder (Depthwise Separable Conv + Multi-Head Self-Attention) - Implement Temporal Cross-Attention Projector Bridge (K=8 query tokens, d=896) - Add zero-cloud On-Device Clinical RAG engine (< 25MB) with ACC/AHA and ESC guideline retrieval - Distillation pipeline for MedGemma-to-Qwen2.5-0.5B with 4-bit block-wise quantization - Add Apple Core ML (ANE/Metal) and Android LiteRT (Qualcomm Hexagon/GGUF) mobile export pipelines - Overhaul README.md, DOCUMENTATION.md, Colab notebook, and interactive dashboard - Pass all 7/7 architecture/budget tests and 8/8 API/safety waiver tests201095b -
Initial commit: MedGemma-Micro multimodal cardiology edge model with lifestyle management & legal waiver guard
dafcd87