1 slices:
2 - sources:
3 - model: TencentARC/LLaMA-Pro-8B-Instruct
4 layer_range: [0, 40]
5 - model: arcee-ai/Patent-Instruct-Extended
6 layer_range: [0, 40]
7 merge_method: slerp
8 base_model: TencentARC/LLaMA-Pro-8B-Instruct
9 parameters:
10 t:
11 - filter: self_attn
12 value: [0, 0.5, 0.3, 0.7, 1]
13 - filter: mlp
14 value: [1, 0.5, 0.7, 0.3, 0]
15 - value: 0.5
16 dtype: bfloat16
17