This repo contains GGUF quantizations of
kunoichi-lemon-royale-7B.
Lightly tested with both Alpaca and ChatML prompts. Works with temperature 1.0 and minP 0.01, but feel free to vary it up. Tested to 8K context.
This model has a tendency to lean into revealing character interiority when generating narrative, which some people might find interesting. I found the model good with not only following the character card but also taking strong hints from the first message. Model is experimental and may occasionally misbehave.
This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
DARE TIES merge method using
SanjiWatsuki/Kunoichi-7B as a base. Each of the models had strengths I liked to varying degrees, leading to weights and densities being adjusted in aesthetic proportion.
1models:
2 - model: SanjiWatsuki/Kunoichi-7B
3 # no parameters necessary for base model
4 - model: KatyTheCutie/LemonadeRP-4.5.3
5 parameters:
6 weight: 0.3
7 density: 0.4
8 - model: core-3/kuno-royale-v2-7b
9 parameters:
10 weight: 0.3
11 density: 0.4
12 - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
13 parameters:
14 weight: 0.4
15 density: 0.8
16merge_method: dare_ties
17base_model: SanjiWatsuki/Kunoichi-7B
18parameters:
19 int8_mask: true
20 normalize: true
21dtype: bfloat16
22
