Update README.md

README.md

@@ -131,7 +131,7 @@ Models used:
 
 [ https://huggingface.co/microsoft/Orca-2-13b ] 
 
-Jeb Carter:
+Jeb Carter's original:
 
 [ https://huggingface.co/jebcarter/psyonic-cetacean-20B ] 
 
@@ -150,6 +150,8 @@ Parts of these models were "grafted" / "fused" together to create this model.
 This 13B version was built using "DARE-TIES" full scale (instead of gradient) method rather than a "pass-through" method which
 was used to create the original/Ultra 20B Psyonic Cetacean.
 
+LLaMA2-13B-Psyfighter2 was recreated using the same mergekit formula, but preserved at float 32 instead of float16.
+
 <b>Optional Enhancement:</B>
 
 The following can be used in place of the "system prompt" or "system role" to further enhance the model.