Update README.md

README.md

@@ -15,3 +15,20 @@ It is hierarchical SLERP merged from the following models
   * meta-math/MetaMath-Mistral-7B (Apache 2.0)
   * openchat/openchat-3.5-1210 (Apache 2.0)
 
+Here's how we did the hierarchical SLERP merge.
+```
+                [flux-base-optimized]
+                         ↑
+                     [mistral]
+                         |
+               [stage-1]-+-[openchat]
+                   ↑
+               [mistral]
+                   |
+         [stage-0]-+-[meta-math]
+             ↑
+         [mistral]
+             |
+[openhermes]-+-[neural-chat]
+```
+