16 lines
403 B
YAML
16 lines
403 B
YAML
slices:
|
|
- sources:
|
|
- model: Qwen/Qwen2.5-Coder-7B-Instruct
|
|
layer_range: [0, 28]
|
|
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
|
|
layer_range: [0, 28]
|
|
merge_method: slerp
|
|
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
|
|
parameters:
|
|
t:
|
|
- filter: self_attn
|
|
value: [0, 0.5, 0.3, 0.7, 1]
|
|
- filter: mlp
|
|
value: [1, 0.5, 0.7, 0.3, 0]
|
|
- value: 0.5
|
|
dtype: float16 |