Views
No views yet
1base_model: Qwen/Qwen2.5-3B
2dtype: bfloat16
3forge_method: task_arithmetic
4modules:
5 default:
6 slices:
7 - sources:
8 - layer_range: [0, 36]
9 model: Qwen/Qwen2.5-Coder-3B-Instruct
10 parameters:
11 weight: 0.5
12 - layer_range: [0, 36]
13 model: Qwen/Qwen2.5-3B