slices: | |
- sources: | |
- model: Qwen/Qwen2.5-7B-Instruct | |
layer_range: [0, 7] | |
- model: Qwen/Qwen2.5-Math-7B-Instruct | |
layer_range: [0, 7] | |
parameters: | |
weight: [0.85, 0.15] | |
nuslerp_flatten: false | |
- sources: | |
- model: Qwen/Qwen2.5-7B-Instruct | |
layer_range: [7, 14] | |
- model: Qwen/Qwen2.5-Math-7B-Instruct | |
layer_range: [7, 14] | |
parameters: | |
weight: [0.6, 0.4] | |
nuslerp_flatten: false | |
- sources: | |
- model: Qwen/Qwen2.5-7B-Instruct | |
layer_range: [14, 21] | |
- model: Qwen/Qwen2.5-Math-7B-Instruct | |
layer_range: [14, 21] | |
parameters: | |
weight: [0.4, 0.6] | |
nuslerp_flatten: false | |
- sources: | |
- model: Qwen/Qwen2.5-7B-Instruct | |
layer_range: [21, 28] | |
- model: Qwen/Qwen2.5-Math-7B-Instruct | |
layer_range: [21, 28] | |
parameters: | |
weight: [0.3, 0.7] | |
nuslerp_flatten: false | |
merge_method: nuslerp | |
dtype: float16 | |