File size: 240 Bytes
3f37ba4
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
base_model: Qwen-Qwen2.5-1.5B-Instruct
models:
  - model: Qwen2.5-1.5B-gsm8k-grpo-full
    parameters:
      weight: 1.0
  - model: Qwen2.5-1.5B-gsm8k-sft-full
    parameters:
      weight: -1.0
merge_method: task_arithmetic
dtype: bfloat16