This is a merge of pre-trained language models created using
mergekit. There are no higher quants available for this model, only one due to hardware limitations.
This model was merged using the
DARE TIES merge method using
PocketDoc/Dans-PersonalityEngine-V1.3.0-24b as a base.
The intention of this merge is to essensially make a model that is capable of roleplaying in NSFW,SFW settings all in one, with smarts involved. Moreover overlap multiple unique writing styles.
1models:
2 - model: Delta-Vector/MS3.2-Austral-24B-KTO
3 parameters:
4 weight: 0.3
5 density: 0.3
6 - model: Delta-Vector/Austral-24B-Winton
7 parameters:
8 weight: 0.3
9 density: 0.5
10 - model: ReadyArt/The-Omega-Directive-M-24B-v1.1
11 parameters:
12 weight: 0.2
13 density: 0.3
14merge_method: ties
15base_model: PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
16dtype: bfloat16
17outtype: bfloat16
The prompting format is refered to as Dan's chat for this model.
I would advise starting with adaptive.p at the settings:
target: 0,55
decay: 0.9
min_p: 0.04
You are free to experiment to set samplers to your liking, this model is under testing phase and users are free to experiment with samplers. The only main requirement is Prompt guide.
