This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
task arithmetic merge method using
FourOhFour/Zenith_4B as a base.
1merge_method: task_arithmetic
2base_model: FourOhFour/Zenith_4B
3parameters:
4 normalize: true
5models:
6 - model: FourOhFour/Deedlit_4B
7 parameters:
8 weight: 0.3
9 - model: FourOhFour/NeuroCom_4B
10 parameters:
11 weight: 0.1
12 - model: FourOhFour/NeuroCom_v2_4B
13 parameters:
14 weight: 0.1
15 - model: FourOhFour/Zenith_4B
16 parameters:
17 weight: 0.3
18 - model: FourOhFour/QuantuMinx_4B
19 parameters:
20 weight: 0.1
21 - model: FourOhFour/Luxe_4B
22 parameters:
23 weight: 0.2
24 - model: FourOhFour/Maelstrom_4B
25 parameters:
26 weight: 0.1
27 - model: FourOhFour/Poe_4B
28 parameters:
29 weight: 0.1
30dtype: bfloat16
