NeutralGear_24B_V.2

This is a merge of pre-trained language models

Goal of this merge was to create model, capable to true neutral or dark and extremely unsafe styles of roleplay.

Subgoal was to have good erp capabilities.

It seems, this time goals were reached.

Model is stable, follows given formatting, smart and creative enough. Instructions are followed good.

Lenght of replies is medium, not too short, not too long.

Also, i noticed that model has good attention to char card and context, for 24b mistral.

Ru is supported.

Tested on Mistral- tekken v7 preset, modified shingane v.1 sysprompt. T0.81, XTC 0.1 0.1.