CK0607/Tie-Merged-Qwen-nemotron

merged-model-nemotron

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Linear merge method.

Models Merged

The following models were included in the merge:

• Qwen/Qwen2.5-Math-7B-Instruct
• nvidia/AceMath-7B-Instruct
• nvidia/OpenMath-Nemotron-7B
• deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Configuration

The following YAML configuration was used to produce this model:

models:
 - model: nvidia/AceMath-7B-Instruct
   parameters:
     weight: 0.5
 - model: Qwen/Qwen2.5-Math-7B-Instruct
   parameters:
     weight: 0.15
 - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
   parameters:
     weight: 0.30
 - model: nvidia/OpenMath-Nemotron-7B
   parameters:
     weight: 0.05


merge_method: linear
dtype: float16