Update README.md

README.md

@@ -31,4 +31,4 @@ Russian capabilities preserved, on full ru cards model works slightly better tha
 
 Can write for user and generate some cliche, but it fixes easily by prompt and samplers. I like how it responds on t1.01 /t1.1, top p 0.95, min p 0.05, with XTC 0.1 0.1 (or 0.1 0.3) 
 
-Tested on various character cards and some adventures. Total responses ~600, Used ChatML format. Mistral format is supported, model's replies completely differently, i recommend give a try to both and compare what you like more.
+Tested on various character cards and some adventures. Total responses ~600, Used ChatML format. Mistral format is supported, model replies completely differently, i recommend give a try to both and compare what you like more.