This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
DELLA merge method using
Qwen/Qwen2.5-32B as a base.
1models:
2 - model: Azure99/Blossom-V6-32B
3 parameters:
4 density: 1
5 weight: 1
6 lambda: 0.9
7 - model: arcee-ai/Virtuoso-Medium-v2
8 parameters:
9 density: 1
10 weight: 1
11 lambda: 0.9
12merge_method: della
13base_model: Qwen/Qwen2.5-32B
14parameters:
15 density: 1
16 weight: 1
17 lambda: 0.9
18 normalize: true
19 int8_mask: true
20dtype: bfloat16
21tokenizer_source: base
