---
base_model:
- cutelemonlili/Qwen2.5-1.5B-Instruct_MATH_training_response_Qwen2.5_14B
- Xiaojian9992024/Qwen2.5-Ultra-1.5B-25.02-Exp
- UWNSL/Qwen2.5-1.5B-Instruct_Short_CoT
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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [Xiaojian9992024/Qwen2.5-Ultra-1.5B-25.02-Exp](https://huggingface.co/Xiaojian9992024/Qwen2.5-Ultra-1.5B-25.02-Exp) as a base.

### Models Merged

The following models were included in the merge:
* [cutelemonlili/Qwen2.5-1.5B-Instruct_MATH_training_response_Qwen2.5_14B](https://huggingface.co/cutelemonlili/Qwen2.5-1.5B-Instruct_MATH_training_response_Qwen2.5_14B)
* [UWNSL/Qwen2.5-1.5B-Instruct_Short_CoT](https://huggingface.co/UWNSL/Qwen2.5-1.5B-Instruct_Short_CoT)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Xiaojian9992024/Qwen2.5-Ultra-1.5B-25.02-Exp
    #no parameters necessary for base model
  - model: UWNSL/Qwen2.5-1.5B-Instruct_Short_CoT
    parameters:
      density: 0.5
      weight: 0.5
  - model: cutelemonlili/Qwen2.5-1.5B-Instruct_MATH_training_response_Qwen2.5_14B
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: Xiaojian9992024/Qwen2.5-Ultra-1.5B-25.02-Exp
parameters:
  normalize: false
  int8_mask: true
dtype: float16
```