|
merge_method: passthrough |
|
slices: |
|
- sources: |
|
- layer_range: [0, 19] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
- sources: |
|
- layer_range: [19, 20] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
- sources: |
|
- layer_range: [19, 20] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [19, 20] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [20, 21] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
- sources: |
|
- layer_range: [20, 21] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [20, 21] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [21, 22] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
- sources: |
|
- layer_range: [21, 22] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [21, 22] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [22, 23] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
- sources: |
|
- layer_range: [22, 23] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [22, 23] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [23, 24] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
- sources: |
|
- layer_range: [23, 24] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [23, 24] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [24, 25] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
- sources: |
|
- layer_range: [24, 25] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [24, 25] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [25, 26] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
- sources: |
|
- layer_range: [25, 26] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [25, 26] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [26, 27] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
- sources: |
|
- layer_range: [26, 27] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [26, 27] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [27, 28] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
- sources: |
|
- layer_range: [27, 28] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [27, 28] |
|
model: Qwen/Qwen2.5-7B-Instruct |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |