Link the public single-commit code release

README.md

@@ -14,12 +14,12 @@ measured results. This repository stays private during testing.
 
 ## Setup
 
-GitHub installation only; nothing is published to PyPI. A CUDA GPU is recommended.
+GitHub installation only; nothing is published to PyPI.
 
 ```bash
 python -m venv .venv
 source .venv/bin/activate
-pip install "git+https://github.com/helblazer811/FlowMapReasoning.git@public-simplified"
+pip install "git+https://github.com/helblazer811/Flow-Reasoning-Models.git"
 hf auth login  # while this model repository is private
 ```
 
@@ -81,8 +81,7 @@ hash. Optimizer state is omitted; raw weights and EMA are retained. These are co
 For training from scratch, download `training.yaml` and run
 `python -m frm.train --config training.yaml` on the matching data.
 
-Code is being drafted on
-[public-simplified](https://github.com/helblazer811/FlowMapReasoning/tree/public-simplified).
-The final standalone GitHub repository will receive one clean commit after release
-validation; the draft branch history is preserved. This lightweight release supports
+Training and evaluation code is available in
+[Flow-Reasoning-Models](https://github.com/helblazer811/Flow-Reasoning-Models).
+This lightweight release supports
 the models and evaluations above, not every paper baseline, ablation, table or figure.