This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
DARE TIES merge method using
nbeerbower/gemma2-gutenberg-9B as a base.
1merge_method: dare_ties
2models:
3 - model: nbeerbower/gemma2-gutenberg-9B
4 parameters:
5 weight: 0.25
6 - model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
7 parameters:
8 weight: 0.25
9 - model: ifable/gemma-2-Ifable-9B
10 parameters:
11 weight: 0.25
12 - model: lemon07r/Gemma-2-Ataraxy-9B
13 parameters:
14 weight: 0.25
15base_model: nbeerbower/gemma2-gutenberg-9B
16parameters:
17 t: [0, 0.33, 0.67, 1]
18dtype: bfloat16
