---
base_model:
- Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
- marcuscedricridia/sbr-o1-7b
- marcuscedricridia/olmner-della-7b
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-Dyanka-7B-Preview](https://huggingface.co/Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview) as a base.

### Models Merged

The following models were included in the merge:
* [marcuscedricridia/sbr-o1-7b](https://huggingface.co/marcuscedricridia/sbr-o1-7b)
* [marcuscedricridia/olmner-della-7b](https://huggingface.co/marcuscedricridia/olmner-della-7b)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
model_name: "cursa-o1-7b"
models:
  - model: Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
    #no parameters necessary for base model
  - model: marcuscedricridia/sbr-o1-7b
    parameters:
      density: 0.5
      weight: 0.66
  - model: marcuscedricridia/olmner-della-7b
    parameters:
      density: 0.5
      weight: 0.66

merge_method: ties
base_model: Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16
tokenizer_source: "union"  # or "base" or a model path
chat_template: "auto"  # or a template name or Jinja2 template
```