Update README.md

README.md

@@ -13,7 +13,8 @@ We work on making small language models punch far above their weight while remai
 These are our models:
 
 ### Astral
-> Astral is our first open-data model, based on Qwen-3 4B 2507, trained for STEM usage.
+> Astral is our first open-data family, trained for STEM usage.
+- Astral 14B (https://huggingface.co/LucidityAI/Astral-14B)
 - Astral 4B Preview (https://huggingface.co/LucidityAI/Astral-4B-Preview)
 
 ### Synth