# SMB with instruct to help performance. | |
slices: | |
- sources: | |
- model: g:/11b/Mistral-Nemo-Instruct-2407-12B | |
layer_range: [0, 14] | |
- sources: | |
- model: G:/11B/magnum-v2.5-12b-kto | |
layer_range: [8, 24] | |
parameters: | |
scale: | |
- filter: o_proj | |
value: 1 | |
- filter: down_proj | |
value: 1 | |
- value: 1 | |
- sources: | |
- model: g:/11b/Mistral-Nemo-Instruct-2407-12B | |
layer_range: [14, 22] | |
parameters: | |
scale: | |
- filter: o_proj | |
value: .5 | |
- filter: down_proj | |
value: .5 | |
- value: 1 | |
- sources: | |
- model: g:/11b/Mistral-Nemo-Instruct-2407-12B | |
layer_range: [22, 31] | |
parameters: | |
scale: | |
- filter: o_proj | |
value: .75 | |
- filter: down_proj | |
value: .75 | |
- value: 1 | |
- sources: | |
- model: G:/11B/magnum-v2.5-12b-kto | |
layer_range: [24, 40] | |
parameters: | |
scale: | |
- filter: o_proj | |
value: 1 | |
- filter: down_proj | |
value: 1 | |
- value: 1 | |
merge_method: passthrough | |
dtype: bfloat16 |