Deepseek-R1-Distill-14B-MMC / fusechat-sce.yml
realYinkaIyiola's picture
Upload folder using huggingface_hub
9187768 verified
raw
history blame contribute delete
284 Bytes
models:
# Pivot model
- model: Qwen/Qwen2.5-14B
# Target models
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
- model: realYinkaIyiola/Deepseek-R1-Distill-14B-Math-Code-Merged
merge_method: sce
base_model: Qwen/Qwen2.5-14B
parameters:
select_topk: 1.0
dtype: bfloat16