This is a merge of pre-trained language models created using
mergekit.
I liked both of the models, used mainly for RP. Tests and feedback is appreciated. The GGUF-imatrix quants are here
GGUF quantsThis model was merged using the
SLERP merge method.
1slices:
2 - sources:
3 - model: ChaoticNeutrals/Captain-Eris_Twilight-V0.420-12B
4 layer_range: [0, 40]
5 - model: inflatebot/MN-12B-Mag-Mell-R1
6 layer_range: [0, 40]
7merge_method: slerp
8base_model: ChaoticNeutrals/Captain-Eris_Twilight-V0.420-12B
9parameters:
10 t:
11 - filter: self_attn
12 value: [0, 0.5, 0.3, 0.7, 1]
13 - filter: mlp
14 value: [1, 0.5, 0.7, 0.3, 0]
15 - value: 0.3
16dtype: bfloat16
