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-121 as a base.
1
2models:
3 - model: deepnetguy/gemma-121
4 # No parameters necessary for base model
5 - model: deepnetguy/gemma-118
6 parameters:
7 density: 0.53
8 weight: 0.33
9 - model: rwh/gemma2
10 parameters:
11 density: 0.53
12 weight: 0.3
13 - model: tomaszki/gemma-42
14 parameters:
15 density: 0.53
16 weight: 0.4
17merge_method: dare_ties
18base_model: deepnetguy/gemma-121
19parameters:
20 int8_mask: true
21dtype: bfloat16
22
23
