# Modification notice

This repository contains a study-specific LoRA adapter derived from `google/txgemma-2b-predict`.

- The upstream Google base-model weights are **not** included.
- The distributed `adapter_model.safetensors` contains LoRA parameters produced by study-specific fine-tuning.
- The distributed `adapter_config.json` records the adapter configuration, including LoRA rank `r = 8` and LoRA alpha `8`.
- The released artifact corresponds to the selected **210,000-step checkpoint** used for PGx representation extraction in the associated manuscript.
- The files under `examples/` are synthetic/illustrative release materials and are not real patient records.

Use and redistribution are subject to the Health AI Developer Foundations Terms of Use referenced in `README.md` and `NOTICE`.