Update README.md

README.md

@@ -1,10 +1,38 @@
 ---
-base_model: Qwen/Qwen3-14B
+base_model: Qwen/Qwen3-4B
+datasets:
+- LucidityAI/Astral-Post-Training-Dataset
 tags:
-- merge
-- lora
+- code
+- chemistry
+- finance
+- biology
 ---
 
-# Astral-14B
+# Astral-4B
 
-Merged LoRA model based on Qwen3-14B.
+Astral 4B is the medium sized model in the Astral family. It was fine-tuned from Qwen3 4b on LucidityAI/Astral-Post-Training-Dataset. 
+
+
+As with usual Qwen3 models, reasoning can be toggled through the usage of ```/no_think``` or not.
+
+
+### Example Prompt (ChatML Format (THINKING)):
+
+```xml
+<|im_start|>user
+What is the capital of France?
+<|im_end|>
+<|im_start|>assistant
+<think>
+```
+
+### Example Prompt (ChatML Format (NON-THINKING)):
+
+```xml
+<|im_start|>user
+What is the capital of France? /no_think
+<|im_end|>
+<|im_start|>assistant
+<think>
+```