---
base_model:
- rinna/bilingual-gpt-neox-4b
- rinna/japanese-gpt-neox-3.6b
library_name: transformers
tags:
- mergekit
- merge
inference: true
license: mit

---
# 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 [rinna/japanese-gpt-neox-3.6b](https://huggingface.co/rinna/japanese-gpt-neox-3.6b) as a base.

### Models Merged

The following models were included in the merge:
* [rinna/bilingual-gpt-neox-4b](https://huggingface.co/rinna/bilingual-gpt-neox-4b)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: rinna/bilingual-gpt-neox-4b
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: rinna/japanese-gpt-neox-3.6b
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: true
dtype: float16
```