Update README.md

README.md

@@ -9,7 +9,7 @@ tags:
 ---
 # Mistral Nemo 12B Starsong
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). Just messing around, thought this one turned out distinct enough? YMMV on that, but I kinda liked it. It's definitely better for SFW than for NSFW tho. <br>
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). Just messing around, thought this one turned out distinct enough? YMMV on that, but I kinda liked it. It's definitely better for SFW than for NSFW tho. Seems to be stabler with Mistral formatting? Weird, both merged models were trained with ChatML. I guess we chalk it up to another merging anomaly, heh.  <br>
 Unlicensed bc I got enlightened (lmao) and don't want to license machine output anymore.<br>
 Thanks to [Sao](https://huggingface.co/Sao10K) for [Lyra](https://huggingface.co/Sao10K/MN-12B-Lyra-v1) btw, really liking the direction where those experimental models are heading. Keep it up!
 ## Merge Details