This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
DARE TIES merge method using
starmpcc/Asclepius-Llama2-13B as a base.
1base_model: starmpcc/Asclepius-Llama2-13B
2dtype: bfloat16
3merge_method: dare_ties
4modules:
5 default:
6 slices:
7 - sources:
8 - layer_range: [0, 40]
9 model: AdaptLLM/finance-LLM-13B
10 parameters:
11 density: 0.53
12 weight: 0.6
13 - layer_range: [0, 40]
14 model: starmpcc/Asclepius-Llama2-13B
15 parameters:
16 density: 0.5
17 weight: 0.4
18parameters:
19 int8_mask: 1.0
