Files
Qwen2.5-1.5b-thinking-task-…/mergekit_config.yml

20 lines
733 B
YAML
Raw Permalink Normal View History

merge_method: task_arithmetic
slices:
- sources:
- model: /workspace/dqdung/khoaluan/model/Qwen2.5-1.5B
layer_range: [0, 28]
- model: /workspace/dqdung/khoaluan/model/Qwen2.5-Math-1.5B-Instruct
layer_range: [0, 28]
parameters:
density: 0.8 # k = 0.8 (top-k% of task vectors to keep)
weight: 0.3 # α = 1.0
- model: /workspace/dqdung/khoaluan/model/DeepSeek-R1-Distill-Qwen-1.5B
layer_range: [0, 28]
parameters:
density: 0.8 # k = 0.8
weight: 0.7 # α = 1.0
merge_parameters:
normalize: false # normalize merged task vectors
dtype: bfloat16
base_model: /workspace/dqdung/khoaluan/model/Qwen2.5-1.5B