Views
No views yet
1base_model: Qwen/Qwen2.5-Coder-1.5B
2dtype: bfloat16
3merge_method: slerp
4modules:
5 default:
6 slices:
7 - sources:
8 - layer_range: [0, 28]
9 model: Qwen/Qwen2.5-Coder-1.5B
10 - layer_range: [0, 28]
11 model: Qwen/Qwen2.5-Math-1.5B
12parameters:
13 t:
14 - filter: self_attn
15 value: [0.15, 0.2, 0.25, 0.3, 0.35]
16 - filter: mlp
17 value: 0.25
18 - value: 0.3
19tokenizer_source: Qwen/Qwen2.5-Coder-1.5B