README.md

---
base_model:
- micaebe/Qwen2.5-1.5B-Instruct-QwQ
- Sakalti/model-4
library_name: transformers
tags:
- mergekit
- merge
inference: true
license: apache-2.0
---
# 概要
由来は鯖から。
# 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 [Sakalti/model-4](https://huggingface.co/Sakalti/model-4) as a base.

### Models Merged

The following models were included in the merge:
* [micaebe/Qwen2.5-1.5B-Instruct-QwQ](https://huggingface.co/micaebe/Qwen2.5-1.5B-Instruct-QwQ)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: micaebe/Qwen2.5-1.5B-Instruct-QwQ
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: Sakalti/model-4
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16
```