valoomba/RombO1-Fuse

RambO1-Fuse

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 Qwen/Qwen2.5-Coder-32B as a base.

Models Merged

The following models were included in the merge:

• FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview
• rombodawg/Rombos-Coder-V2.5-Qwen-32b

Configuration

The following YAML configuration was used to produce this model:

base_model: Qwen/Qwen2.5-Coder-32B
dtype: bfloat16
merge_method: sce
parameters:
  select_topk: 1.0
slices:
- sources:
  - layer_range: [0, 64]
    model: rombodawg/Rombos-Coder-V2.5-Qwen-32b
  - layer_range: [0, 64]
    model: FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview
  - layer_range: [0, 64]
    model: Qwen/Qwen2.5-Coder-32B