This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
TIES merge method using
Qwen/Qwen2.5-7B as a base.
1models:
2 - model: mikun/qwen2.5-9k-lora-model
3 parameters:
4 weight: 1
5 density: 1
6 - model: Qwen/Qwen2.5-7B-Instruct
7 parameters:
8 weight: 1
9 density: 1
10merge_method: ties
11base_model: Qwen/Qwen2.5-7B
12parameters:
13 weight: 1
14 density: 1
15 normalize: true
16 int8_mask: true
17tokenizer_source: mikun/qwen2.5-9k-lora-model
18dtype: bfloat16
19
