This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
DARE TIES merge method using
deepnetguy/gemma-130 as a base.
1
2models:
3 - model: deepnetguy/gemma-130
4 # No parameters necessary for base model
5 - model: rwh/gemma2
6 parameters:
7 density: 0.53
8 weight: 0.3
9 - model: lxsure/gemma_28
10 parameters:
11 density: 0.53
12 weight: 0.25
13 - model: Aspik101/gemmamini14
14 parameters:
15 density: 0.53
16 weight: 0.35
17merge_method: dare_ties
18base_model: deepnetguy/gemma-130
19parameters:
20 int8_mask: true
21dtype: bfloat16
22
23
