---
base_model:
- prithivMLmods/QwQ-LCoT-7B-Instruct
- bunnycore/FuseQwQen-7B
- AIDC-AI/Marco-o1
- happzy2633/qwen2.5-7b-ins-v3
library_name: transformers
tags:
- mergekit
- merge

---
# merge

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [happzy2633/qwen2.5-7b-ins-v3](https://huggingface.co/happzy2633/qwen2.5-7b-ins-v3) as a base.

### Models Merged

The following models were included in the merge:
* [prithivMLmods/QwQ-LCoT-7B-Instruct](https://huggingface.co/prithivMLmods/QwQ-LCoT-7B-Instruct)
* [bunnycore/FuseQwQen-7B](https://huggingface.co/bunnycore/FuseQwQen-7B)
* [AIDC-AI/Marco-o1](https://huggingface.co/AIDC-AI/Marco-o1)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: task_arithmetic
dtype: float32
out_dtype: bfloat16
parameters:
  epsilon: 0.03
  lambda: 0.95
  normalize: true
base_model: happzy2633/qwen2.5-7b-ins-v3
tokenizer_source: happzy2633/qwen2.5-7b-ins-v3
models:
  - model: happzy2633/qwen2.5-7b-ins-v3
    parameters:
      weight: 8
      density: 0.7
  - model: prithivMLmods/QwQ-LCoT-7B-Instruct
    parameters:
      weight: 7
      density: 0.5
  - model: AIDC-AI/Marco-o1
    parameters:
      weight: 8
      density: 0.5
  - model: bunnycore/FuseQwQen-7B
    parameters:
      weight: 8
      density: 0.4
  - model: happzy2633/qwen2.5-7b-ins-v3
    parameters:
      weight: 8
      density: 0.45
```