This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
DARE TIES merge method using
cyberagent/calm2-7b-chat as a base.
1models:
2 - model: cyberagent/calm2-7b-chat
3 # No parameters necessary for base model
4 - model: falche/opennovel_oc2_01a_7b
5 parameters:
6 density: 0.53
7 weight: 0.5
8 - model: offtoung/tsukuyomi-chan-calm2-7b
9 parameters:
10 density: 0.53
11 weight: 0.5
12merge_method: dare_ties
13base_model: cyberagent/calm2-7b-chat
14parameters:
15 int8_mask: true
16dtype: bfloat16
17
