This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
Linear merge method using
NousResearch/Hermes-3-Llama-3.1-8B as a base.
1base_model: NousResearch/Hermes-3-Llama-3.1-8B
2dtype: bfloat16
3merge_method: linear
4modules:
5 default:
6 slices:
7 - sources:
8 - layer_range: [0, 32]
9 model: NousResearch/Hermes-3-Llama-3.1-8B
10 parameters:
11 weight: 0.4
12 - layer_range: [0, 32]
13 model: mlabonne/Meta-Llama-3.1-8B-Instruct-Abliterated
14 parameters:
15 weight: 0.3
16 - layer_range: [0, 32]
17 model: unsloth/Meta-Llama-3.1-8B-Instruct
18 parameters:
19 weight: 0.3
