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/Llama-2-7b-hf as a base.
1
2models:
3 - model: meta-llama/Llama-2-7b-hf
4 - model: meta-llama/CodeLlama-7b-Instruct-hf
5 parameters:
6 density: 0.65
7 weight: 1.0
8 - model: mrm8488/llama-2-coder-7b
9 parameters:
10 density: 0.35
11 weight: 0.5
12merge_method: dare_ties
13base_model: meta-llama/Llama-2-7b-hf
14parameters:
15 int8_mask: true
16dtype: bfloat16
17
