FuseChat: Knowledge Fusion of Chat Models
Paper
•
2408.07990
•
Published
•
14
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SCE merge method using Qwen/Qwen3-4B-Instruct-2507 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: Qwen/Qwen3-4B-Instruct-2507
- model: huihui-ai/Huihui-Qwen3-4B-Instruct-2507-abliterated
merge_method: sce
base_model: Qwen/Qwen3-4B-Instruct-2507
parameters:
select_topk: 1
dtype: bfloat16