Update README.md

README.md

@@ -13,18 +13,21 @@ 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 4B Preview (https://huggingface.co/LucidityAI/Astral-4B-Preview)
 
-### Kiwi
+### Kiwi (Depreciated)
+> Kiwi is a family of models trained for general STEM tasks.
 - Kiwi 1.7B Nano (https://huggingface.co/LucidityAI/kiwi-1.7b-nano)
 - Kiwi 4B Mini (https://huggingface.co/LucidityAI/kiwi-4b)
 - Kiwi 8B (https://huggingface.co/LucidityAI/Kiwi-8b)
 
 ### RedTeamer
+> RedTeamer is a model that generates jailbreaks that can be used for testing against LLMs.
 - RedTeamer 1 (https://huggingface.co/LucidityAI/RedTeamer-v1)
 
 ### Koishi
+> Koishi is a data synthesis LLM that generates CoT traces for non-CoT examples.
 - Koishi 1 (https://huggingface.co/LucidityAI/Koishi-1)
 
 ### Synth