This model is a merge of my personal favourite models, i couldn't decide between them so why not have both? Without MOE cause gpu poor :3
With my own tests it gives kuro-lotus like results without the requirement for a highly detailed character card and stays coherent when roping up to 8K context.
I personally use the "Universal Light" preset in silly tavern, with "alpaca" the results can be short but are longer with "alpaca roleplay".
"Universal Light" preset can be extremely creative but sometimes likes to act for user with some cards, for those i like just the "default" but any preset seems to work!
This is a merge of pre-trained language models created using
mergekit.
This model was merged using the SLERP merge method.
1slices:
2 - sources:
3 - model: saishf/Kuro-Lotus-10.7B
4 layer_range: [0, 48]
5 - model: Sao10K/Fimbulvetr-10.7B-v1
6 layer_range: [0, 48]
7merge_method: slerp
8base_model: saishf/Kuro-Lotus-10.7B
9parameters:
10 t:
11 - filter: self_attn
12 value: [0.6, 0.7, 0.8, 0.9, 1]
13 - filter: mlp
14 value: [0.4, 0.3, 0.2, 0.1, 0]
15 - value: 0.5
16dtype: bfloat16
17
