---
base_model:
- zhiyuanhucs/qwen2.5-7B-formula-1k-base-final-1-step280
- zhiyuanhucs/qwen2.5-7b-sequence-200-5
- zhiyuanhucs/qwen2.5-7b-backward-reasoning-7B-level-2-0310
library_name: transformers
tags:
- mergekit
- merge

---
# linear4

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 [Linear](https://arxiv.org/abs/2203.05482) merge method.

### Models Merged

The following models were included in the merge:
* [zhiyuanhucs/qwen2.5-7B-formula-1k-base-final-1-step280](https://huggingface.co/zhiyuanhucs/qwen2.5-7B-formula-1k-base-final-1-step280)
* [zhiyuanhucs/qwen2.5-7b-sequence-200-5](https://huggingface.co/zhiyuanhucs/qwen2.5-7b-sequence-200-5)
* [zhiyuanhucs/qwen2.5-7b-backward-reasoning-7B-level-2-0310](https://huggingface.co/zhiyuanhucs/qwen2.5-7b-backward-reasoning-7B-level-2-0310)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: zhiyuanhucs/qwen2.5-7B-formula-1k-base-final-1-step280
    parameters:
      weight: 0.15
  - model: zhiyuanhucs/qwen2.5-7b-sequence-200-5
    parameters:
      weight: 0.15
  - model: zhiyuanhucs/qwen2.5-7b-backward-reasoning-7B-level-2-0310
    parameters:
      weight: 0.7
merge_method: linear
dtype: float32


```