This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
task arithmetic merge method using
openaccess-ai-collective/DPOpenHermes-7B-v2 as a base.
1base_model: openaccess-ai-collective/DPOpenHermes-7B-v2
2dtype: bfloat16
3merge_method: task_arithmetic
4slices:
5- sources:
6 - layer_range: [0, 32]
7 model: openaccess-ai-collective/DPOpenHermes-7B-v2
8 - layer_range: [0, 32]
9 model: merged
10 parameters:
11 weight: 0.5
12 - layer_range: [0, 32]
13 model: SanjiWatsuki/Lelantos-7B
14 parameters:
15 weight: 0.5
Detailed results can be found
here
