This is a merge of pre-trained language models created using
mergekit.
This model was merged using the della_linear merge method using
Undi95/Utopia-13B as a base.
1models:
2 - model: cognitivecomputations/WizardLM-1.0-Uncensored-Llama2-13b
3 parameters:
4 weight: 0.5
5 density: 0.8
6 - model: cognitivecomputations/WizardLM-1.0-Uncensored-Llama2-13b
7 parameters:
8 weight: 0.5
9 density: 0.8
10merge_method: della_linear
11base_model: Undi95/Utopia-13B
12parameters:
13 epsilon: 0.05
14 lambda: 1
15 int8_mask: true
16dtype: bfloat16
17tokenzer_source: union
18
