This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
DELLA merge method using
Qwen/Qwen2.5-7B as a base.
1base_model: Qwen/Qwen2.5-7B
2dtype: float16
3merge_method: della
4modules:
5 default:
6 slices:
7 - sources:
8 - layer_range: [0, 28]
9 model: Alelcv27/Qwen2.5-7B-Math-CoT
10 parameters:
11 density: 0.8
12 weight: 0.7
13 - layer_range: [0, 28]
14 model: Qwen/Qwen2.5-7B-Instruct
15 parameters:
16 density: 0.8
17 weight: 0.5
18 - layer_range: [0, 28]
19 model: Qwen/Qwen2.5-7B
20parameters:
21 epsilon: 0.1
22 lambda: 0.9
23 normalize: 1.0
