|
slices: |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [0,25] |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [25,26] |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [25,26] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [25,26] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [26,27] |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [26,27] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [26,27] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [27,28] |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [27,28] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [27,28] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [28,29] |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [28,29] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [28,29] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [29,30] |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [29,30] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [29,30] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [30,31] |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [30,31] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [30,31] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [31,32] |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [31,32] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [31,32] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [32,33] |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [32,33] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [32,33] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [33,34] |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [33,34] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [33,34] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [34,35] |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [34,35] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [34,35] |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- model: Qwen/Qwen3-14B-Base |
|
layer_range: [35,40] |
|
merge_method: passthrough |