metadata
base_model:
- qihoo360/Light-R1-32B-DS
- Gen-Verse/ReasonFlux-F1
- Skywork/Skywork-OR1-32B-Preview
- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
- qihoo360/TinyR1-32B-Preview
library_name: transformers
tags:
- mergekit
- merge
new_version: YOYO-AI/DS-R1-Distill-32B-SCE-V2
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SCE merge method using deepseek-ai/DeepSeek-R1-Distill-Qwen-32B as a base.
Models Merged
The following models were included in the merge:
- qihoo360/Light-R1-32B-DS
- Gen-Verse/ReasonFlux-F1
- Skywork/Skywork-OR1-32B-Preview
- qihoo360/TinyR1-32B-Preview
Configuration
The following YAML configuration was used to produce this model:
merge_method: sce
models:
# Pivot model
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
# Target models
- model: qihoo360/Light-R1-32B-DS
- model: qihoo360/TinyR1-32B-Preview
- model: Gen-Verse/ReasonFlux-F1
- model: Skywork/Skywork-OR1-32B-Preview
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
parameters:
select_topk: 1
dtype: bfloat16
tokenizer_source: qihoo360/Light-R1-32B-DS
normalize: true
int8_mask: true