This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
TIES merge method using
cognitivecomputations/dolphin-2.8-mistral-7b-v02 as a base.
1models:
2 - model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
3 parameters:
4 density: 0.5
5 weight: 0.5
6 - model: Rakuten/RakutenAI-7B-chat
7 parameters:
8 density: 0.5
9 weight: 0.5
10
11merge_method: ties
12base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
13parameters:
14 normalize: false
15 int8_mask: true
16dtype: float16