FuseChat: Knowledge Fusion of Chat Models
Paper • 2408.07990 • Published • 15
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SCE merge method using deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
# Pivot model
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
# Target models
- model: Qwen/Qwen2.5-1.5B-Instruct
- model: nvidia/AceMath-1.5B-Instruct
- model: nvidia/AceInstruct-1.5B
merge_method: sce
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
parameters:
select_topk: 1.5
dtype: bfloat16