FuseChat: Knowledge Fusion of Chat Models
Paper
β’
2408.07990
β’
Published
β’
14
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SCE merge method using bunnycore/Qwen2.5-7B-RRP-1M as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: bunnycore/Qwen2.5-7B-MixStock-V0.1
- model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1
- model: open-thoughts/OpenThinker-7B
- model: bunnycore/Qwen2.5-7B-RRP-1M
merge_method: sce
base_model: bunnycore/Qwen2.5-7B-RRP-1M
parameters:
select_topk: 1.5
dtype: bfloat16