---
base_model:
- Casual-Autopsy/Llama-3-Shisa-Minus-Base
- Casual-Autopsy/Llama-3-Youko-Minus-Base
- Casual-Autopsy/Llama-3-Minus-Base
- Casual-Autopsy/Llama-3-Yollow-SCE-TopK_1.0
- Casual-Autopsy/vntl-qlora
- Casual-Autopsy/Llama-3-Swallow-Minus-Base
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 [Casual-Autopsy/Llama-3-Yollow-SCE-TopK_1.0](https://huggingface.co/Casual-Autopsy/Llama-3-Yollow-SCE-TopK_1.0) + [Casual-Autopsy/vntl-qlora](https://huggingface.co/Casual-Autopsy/vntl-qlora) as a base.

### Models Merged

The following models were included in the merge:
* [Casual-Autopsy/Llama-3-Shisa-Minus-Base](https://huggingface.co/Casual-Autopsy/Llama-3-Shisa-Minus-Base)
* [Casual-Autopsy/Llama-3-Youko-Minus-Base](https://huggingface.co/Casual-Autopsy/Llama-3-Youko-Minus-Base)
* [Casual-Autopsy/Llama-3-Minus-Base](https://huggingface.co/Casual-Autopsy/Llama-3-Minus-Base)
* [Casual-Autopsy/Llama-3-Swallow-Minus-Base](https://huggingface.co/Casual-Autopsy/Llama-3-Swallow-Minus-Base)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  # Base
  - model: Casual-Autopsy/Llama-3-Yollow-SCE-TopK_1.0+Casual-Autopsy/vntl-qlora
    parameters:
      weight: 1.0
  # Models
  - model: Casual-Autopsy/Llama-3-Minus-Base
    parameters:
      density: 0.35
      weight: 10e-5
  - model: Casual-Autopsy/Llama-3-Shisa-Minus-Base
    parameters:
      density: 0.85
      weight: 25e-5
  - model: Casual-Autopsy/Llama-3-Swallow-Minus-Base
    parameters:
      density: 0.85
      weight: 25e-5
  - model: Casual-Autopsy/Llama-3-Youko-Minus-Base
    parameters:
      density: 0.85
      weight: 25e-5
merge_method: ties
base_model: Casual-Autopsy/Llama-3-Yollow-SCE-TopK_1.0+Casual-Autopsy/vntl-qlora
parameters:
  normalize: false
  int8_mask: false
dtype: float32
```