S1.1-Deepseek-R1-T1-32B / fusechat-sce.yml
radna's picture
Upload folder using huggingface_hub
2f613ba verified
models:
# Pivot model
- model: Qwen/Qwen2.5-32B
# Target models
- model: simplescaling/s1.1-32B
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
- model: NovaSky-AI/Sky-T1-32B-Preview
merge_method: sce
base_model: Qwen/Qwen2.5-32B
parameters:
select_topk: 1.0
dtype: bfloat16