Views
No views yet
1merge_method: slerp
2base_model:
3 model: Qwen/Qwen2.5-Coder-32B-Instruct # Define the base model explicitly
4slices:
5 - sources:
6 - model: Qwen/Qwen2.5-Coder-32B-Instruct
7 layer_range:
8 - 0
9 - 32
10 - model: Qwen/QwQ-32B-Preview
11 layer_range:
12 - 0
13 - 32
14 parameters:
15 t:
16 - filter: self_attn
17 value:
18 - 0
19 - 0.5
20 - 0.3
21 - 0.7
22 - 1
23 - filter: mlp
24 value:
25 - 1
26 - 0.5
27 - 0.7
28 - 0.3
29 - 0
30 - value: 0.5
31dtype: bfloat16