Update README.md

README.md

@@ -23,21 +23,22 @@ This special edition went thru UNA at MLP layers just like [miniclaus-1.5B](http
 
 Here we use our novel approach called `MGS`. Its up to you to figure out what it means. On top of that we used `UNA: Uniform Neural Alignment`
 
-Cybertron V4 went thru SFT with MGS & UNA  over `Magpie-Align/Magpie-Qwen2.5-Pro-1M-v0.1`
+Cybertron V4 went thru SFT with `MGS & UNA`  over `Magpie-Align/Magpie-Qwen2.5-Pro-1M-v0.1` dataset.
 
 ## Quantz
 Soon..
 
-## MGS & UNA
-Being fair:
+## MGS & UNA & Details
 
-https://arxiv.org/pdf/2410.21228
+* MGS, among other things.. a strategy of tackling corpora forgetful. `1+1 = 2 and not 3`
+* UNA, among other things.. orthogonal approach for neural uniformit. `1+1 = 2 obviously`
 
-MGS, among other things.. a strategy of tackling corpora forgetful. `1+1 = 2 and not 3`
-UNA, among other things.. orthogonal approach for neural uniformit. `1+1 = 2 obviously`
+We also followed https://arxiv.org/pdf/2410.21228 insights.
 
 ## Training procedure
+
 1 Epoch as usual.
+
 [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
 ```
 datasets: