This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
SLERP merge method.
1merge_method: slerp
2slices:
3 - sources:
4 - model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
5 layer_range: [0, 40]
6 - model: AlexCuadron/dpo_roleplay
7 layer_range: [0, 40]
8 base_model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
9 parameters:
10 t:
11 - filter: self_attn
12 value: [0.6, 0.5, 0.5, 0.4, 0.3]
13 - filter: mlp
14 value: [0.4, 0.5, 0.5, 0.7, 0.8]
15 - filter: "layer=[0:10]"
16 value: 0.5
17 - filter: "layer=[30:40]"
18 value: 0.6
19 - value: 0.65
20 dtype: bfloat16
