Update README.md

README.md

@@ -18,6 +18,4 @@ as donor model.
 
 It used 160GB of system ram to merge these models, they merge fast without swap.
 
-For prompt template and model information see [huginnV1](https://huggingface.co/The-Face-Of-Goonery/Huginn-13b-FP16).
-
-This is probably my most coherent 22b model, this 22B model can still output spelling errors though.
+For prompt template and model information see [huginnV1](https://huggingface.co/The-Face-Of-Goonery/Huginn-13b-FP16).