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 Improved merge method using Qwen/Qwen2.5-VL-7B-Instruct as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: sce
base_model: Qwen/Qwen2.5-VL-7B-Instruct
models:
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B