The goal was creating good/stable Role-Play model with merging multiple models with multiple steps.

Seems like i have created a model that is very stable and creative.

This is a merge of pre-trained language models created using mergekit. Then used Heretic to remove refusals

This model was merged using the Dare-Ties, Model Stock and SLERP merge method.

The following YAML configurations was used to produce this model:

Step 1:

Step 2:

Step 3: