This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
task arithmetic merge method using
NousResearch/Llama-2-7b-hf as a base.
1base_model: NousResearch/Llama-2-7b-hf
2dtype: bfloat16
3merge_method: task_arithmetic
4slices:
5- sources:
6 - layer_range: [0, 32]
7 model: taide/TAIDE-LX-7B
8 parameters:
9 weight: 1.0
10 - layer_range: [0, 32]
11 model: NousResearch/Llama-2-7b-chat-hf
12 parameters:
13 weight: 1.0
14 - layer_range: [0, 32]
15 model: NousResearch/Llama-2-7b-hf
