Update README.md

README.md

@@ -18,7 +18,7 @@ tags:
 
 An RP/Story writing merge of 3 models that all use the mistral prompt and have seen some success at higher context levels. The original models used were Mistral Instruct, Mini-Magnum, and Lyra-v1. These models then had extra dpo/orpo training done on top to enhance there already good creative capabilities.
 
-Slight divergence with this 1.3 version. The RP specific models got a slight boost in percentages, while the other was decreased in the process. Went back to the old Stew method of merging here as well, where each piece is hyper specific with the percentages chosen. Tried a dozen or so after the 1.2 merge, but this was the only one I liked to where it was both different enough from the other and (seemingly) stable. Might not be a straight upgrade, but it's an interesting side-grade. Something like the XTC sampler would probably work well for this one, but not sure at what levels yet.
+Slight divergence with this 1.3 version. The RP specific models got a slight boost in percentages, while the other was decreased in the process. Went back to the old Stew method of merging here as well, where each piece is hyper specific with the percentages chosen. Tried a dozen or so after the 1.2 merge, but this was the only one I liked to where it was both different enough from the other and (seemingly) stable. Might not be a straight upgrade, but it's an interesting side-grade.
 
 Big thanks to the MistralAI team, intervitens and his Anthracite team, along with Sao10K for the original models used, plus nbeerbower for the extra training done as well!