slices: | |
- sources: | |
- model: G:/7B/Meta-Llama-3-8B-Instruct | |
layer_range: [0, 12] | |
- sources: | |
- model: G:/7B/L3-8B-Stheno-v3.2 | |
layer_range: [6, 19] | |
parameters: | |
scale: | |
- filter: o_proj | |
value: 1 | |
- filter: down_proj | |
value: 1 | |
- value: 1 | |
- sources: | |
- model: G:/7B/Meta-Llama-3-8B-Instruct | |
layer_range: [12, 18] | |
parameters: | |
scale: | |
- filter: o_proj | |
value: .5 | |
- filter: down_proj | |
value: .5 | |
- value: 1 | |
- sources: | |
- model: G:/7B/Meta-Llama-3-8B-Instruct | |
layer_range: [18, 25] | |
parameters: | |
scale: | |
- filter: o_proj | |
value: .75 | |
- filter: down_proj | |
value: .75 | |
- value: 1 | |
- sources: | |
- model: G:/7B/L3-8B-Stheno-v3.2 | |
layer_range: [19, 32] | |
parameters: | |
scale: | |
- filter: o_proj | |
value: 1 | |
- filter: down_proj | |
value: 1 | |
- value: 1 | |
merge_method: passthrough | |
dtype: float32 |