This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
task arithmetic merge method using
paulml/NeuralOmniBeagleMBX-v3-7B as a base.
1models:
2 - model: paulml/NeuralOmniWestBeaglake-7B
3 parameters:
4 weight: 1
5 - model: FelixChao/Faraday-7B
6 parameters:
7 weight: 1
8 - model: flemmingmiguel/MBX-7B-v3
9 parameters:
10 weight: 1
11 - model: paulml/NeuralOmniBeagleMBX-v3-7B
12 parameters:
13 weight: 1
14merge_method: task_arithmetic
15base_model: paulml/NeuralOmniBeagleMBX-v3-7B
16parameters:
17 normalize: true
18 int8_mask: true
19dtype: float16
20
