This model is intended for fictional storytelling and role-playing, with a focus on more original conversations and less alignment.
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: KatyTheCutie/LemonadeRP-4.5.3
4 layer_range: [0, 32]
5 - model: Nitral-AI/Infinitely-Laydiculous-7B
6 layer_range: [0, 32]
7merge_method: slerp
8base_model: Nitral-AI/Infinitely-Laydiculous-7B
9parameters:
10 t:
11 - filter: self_attn
12 value: [0.7, 0.3, 0.6, 0.2, 0.5]
13 - filter: mlp
14 value: [0.3, 0.7, 0.4, 0.8, 0.5]
15 - value: 0.5
16dtype: bfloat16
17
