---
base_model:
- spacematt/gemma-2-9B-it-blend-2-rebase
- spacematt/Gemma-Lingua-2-9B-it
- allknowingroger/GemmaSlerp5-10B
- spacematt/gemma-2-9B-it-blend-3-rebase
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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [allknowingroger/GemmaSlerp5-10B](https://huggingface.co/allknowingroger/GemmaSlerp5-10B) as a base.

### Models Merged

The following models were included in the merge:
* [spacematt/gemma-2-9B-it-blend-2-rebase](https://huggingface.co/spacematt/gemma-2-9B-it-blend-2-rebase)
* [spacematt/Gemma-Lingua-2-9B-it](https://huggingface.co/spacematt/Gemma-Lingua-2-9B-it)
* [spacematt/gemma-2-9B-it-blend-3-rebase](https://huggingface.co/spacematt/gemma-2-9B-it-blend-3-rebase)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: allknowingroger/GemmaSlerp5-10B
models:
  - model: allknowingroger/GemmaSlerp5-10B
  - model: spacematt/Gemma-Lingua-2-9B-it
    parameters:
      density: 0.6
      weight: 0.9
  - model: spacematt/gemma-2-9B-it-blend-2-rebase
    parameters:
      density: 0.4
      weight: 0.6
  - model: spacematt/gemma-2-9B-it-blend-3-rebase
    parameters:
      density: 0.4
      weight: 0.6
merge_method: dare_ties
parameters:
  int8_mask: true
chat_template: auto
dtype: bfloat16
tokenizer_source: spacematt/Gemma-Lingua-2-9B-it
```