Fixed the current and upcoming versions in the readme

README.md

@@ -44,8 +44,8 @@ model-index:
 - Less stable on very long or morphologically complex words
 
 > Development information
-> - 🚧 **Current version:** v1 (stage 2)
-> - ⏳ **Upcoming release:** v2 (stage 3)
+> - 🚧 **Current version:** Baseline (stage 1)
+> - ⏳ **Upcoming release:** v1 (stage 2)
 >
 > **Note:** As of May 18, 2026, AramT5's training process, which was at stage 4, was reset a baseline level due to inconsistencies found in previous versions of the Serto-Madnḥaya mapping code, which mostly invalidated prior learning efforts