Update README.md

README.md

@@ -57,7 +57,7 @@ In Lmstudio the "Jinja Template" should load by default.
 
 In other apps - use the Deepseek Tokenizer.
 
-Sometimes this model will output Chinese Characters/Symbols (with an English prompt) - regen to clear.
+Sometimes this model will output/think in Chinese Characters/Symbols (with an English prompt) - regen to clear.
 
 Sometimes it will work great, other times it will give "so/so" answers and then sometimes it will bat it out of the park, and past the "state line."
 
@@ -67,13 +67,14 @@ It is all over the map.
 
 Four examples below so you have some idea what this model can do.
 
-Keep in mind this model is six 1.5B parameters models working together, and will not have the power of say a 14B or 32B model.
+Keep in mind this model is six 1.5B parameters models working together, and will not have the power of a 14B or 32B reasoning/thinking model.
 
-Also, this model has 4/6 experts activated.
+Also, this model has 4/6 experts activated by default.
 
 You may want to set 6/6 experts for best results.
 
-This model is also mastered in Float 32, which helped overall model generation and addressed some model issues.
+This model is also mastered in Float 32, which helped overall model generation and addressed some model generation issues
+and oddly seemed to add some new ones (? - Chinese Char/Symb thinking.).
 
 Temp of .4 to .8 is suggested, however it will still operate at much higher temps like 1.8, 2.6 etc.