mergekit_config.yml

# Task Arithmetic
# Each lambda is 0.3, refer to AdaMerging Fig.1 [https://arxiv.org/abs/2310.02575] 
base_model: Qwen/Qwen2.5-7B
models:
  - model: Qwen/Qwen2.5-Math-7B-Instruct
    parameters:
      weight: 1.0
  - model: Qwen/Qwen2.5-Coder-7B-Instruct
    parameters:
      weight: 1.0
merge_method: task_arithmetic
parameters:
  normalize: false
  lambda: 0.3
dtype: float16
tokenizer:
  source: union

#MODEL_NAME=deepseek-ai/deepseek-math-7b-instruct
#MODEL_NAME=deepseek-ai/deepseek-coder-7b-instruct-v1.5