This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
DARE TIES merge method using
meta-llama/Meta-Llama-3-8B as a base.
1models:
2 - model: meta-llama/Meta-Llama-3-8B
3 # no parameters necessary for base model
4 - model: meta-llama/Meta-Llama-3-8B-Instruct
5 parameters:
6 density: 0.5
7 weight: 0.5
8 - model: beomi/Llama-3-Open-Ko-8B
9 parameters:
10 density: 0.7
11 weight: 0.5
12merge_method: dare_ties
13base_model: meta-llama/Meta-Llama-3-8B
14dtype: bfloat16
15
