Upload README.md with huggingface_hub

README.md

@@ -59,10 +59,23 @@ It works in any instruct model. The weights are here if you want them.
 
 ---
 
-> **Status: weights not published yet.** The system prompt below is
-> ready to use today in any instruct model. Train the weights with
-> `python scripts/0X_train_coding.py` on a 16 GB GPU (Colab T4), then
-> re-run it to publish them and this card is replaced automatically.
+> ### Weights not published yet
+>
+> The **system prompt below works today** - paste it into any instruct
+> model and you get this voice immediately, no download needed. That is
+> the fastest way to try it, and it is how the demo Space works.
+>
+> To publish the weights:
+>
+> ```bash
+> # on a 16 GB GPU (Colab T4 is enough)
+> python scripts/06_train_coding.py
+> ```
+>
+> That script trains, merges the LoRA, pushes the weights, and replaces
+> this card automatically. Everything else here is already accurate.
+
+---
 
 ## Quick start