---
base_model:
- shenzhi-wang/Gemma-2-9B-Chinese-Chat
- unsloth/gemma-2-9b-it
- stephenlzc/Gemma-2-9B-Chinese-Chat-Uncensored
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 [unsloth/gemma-2-9b-it](https://huggingface.co/unsloth/gemma-2-9b-it) as a base.

### Models Merged

The following models were included in the merge:
* [shenzhi-wang/Gemma-2-9B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Gemma-2-9B-Chinese-Chat)
* [stephenlzc/Gemma-2-9B-Chinese-Chat-Uncensored](https://huggingface.co/stephenlzc/Gemma-2-9B-Chinese-Chat-Uncensored) (Note that this model's config wasn't correctly setup, so I had to clone it and fix it, but the weights are the same.)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: shenzhi-wang/Gemma-2-9B-Chinese-Chat
    parameters:
      weight: -1
  - model: themex1380/Gemma-2-9B-Chinese-Chat-Uncensored
    parameters:
      weight: 1
merge_method: ties
base_model: unsloth/gemma-2-9b-it
parameters:
  density: 1.0
  normalize: False
  int8_mask: True
dtype: float16
```