S1.1-DeepSeek-R1-Bespoke-32B / fusechat-sce.yml
radna's picture
Upload folder using huggingface_hub
7157ccd verified
models:
# Pivot model
- model: Qwen/Qwen2.5-32B
# Target models
- model: bespokelabs/Bespoke-Stratos-32B
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
- model: simplescaling/s1.1-32B
merge_method: sce
base_model: Qwen/Qwen2.5-32B
parameters:
select_topk: 1.0
dtype: bfloat16