Update README.md

README.md

@@ -53,6 +53,44 @@ It's a little crispier than Awqward, but does generate stable output. Since it i
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b19c1b098c85365af5a83e/Yjln2MIh15loleJR7EpbL.png)
 
+## How to think
+
+This model is very compliant to steering, and has innate chain of thought, so producing nice, formatted, chain of thought results is quite easy.  Below is a very simple proof-of-concept example of how to achieve a thought turn.
+
+#### System Prompt
+```
+You are my assistant. You should be helpful and use <thought></thought> xml.
+
+All responses are in xml format.
+```
+
+#### One Shot
+```
+<thoughts>
+  <thought>Example thought</thought>
+  <idea>I have an idea</idea>
+</thoughts>
+```
+
+#### Request
+```
+Think through how you render 2d polys at different scales.
+```
+
+#### Response
+```
+<response>
+  <thoughts>
+    <thought>When rendering 2D polygons at different scales, it's important to maintain their proportions and visual quality.</thought>
+    <idea>One approach could be using texture atlases for efficient scaling without losing detail.</idea>
+    <thought>Another idea is implementing level-of-detail (LOD) techniques to adjust polygon complexity based on scale.</thought>
+    <idea>We might also consider using shaders to handle dynamic scaling and apply effects smoothly.</idea>
+  </thoughts>
+</response>
+```
+
+I did notice it sometimes drops trailing tags, so you should always validate (and if you are clever, repair) any structured responses.
+
 ## Citation
 
 If you find our work helpful, feel free to give us a cite.