This model equips AlphaMonarch-7B with a strong base of emotional intelligence.
This model was merged using the SLERP merge method.
1slices:
2 - sources:
3 - model: mlabonne/AlphaMonarch-7B
4 layer_range: [0, 32]
5 - model: macadeliccc/WestLake-7b-v2-laser-truthy-dpo
6 layer_range: [0, 32]
7merge_method: slerp
8base_model: mlabonne/AlphaMonarch-7B
9parameters:
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
16dtype: bfloat16
17
18
Detailed results can be found
here
