README.md

---
base_model:
- aks1s/13Aks-18
- starnet/19star03
- OwOpeepeepoopoo/ZZZZZsubmission7
- OwOpeepeepoopoo/ZZZZZsubmission5
- starnet/15star03
- irusl/05Ir-4
library_name: transformers
tags:
- mergekit
- merge

---
# output_2

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 [irusl/05Ir-4](https://huggingface.co/irusl/05Ir-4) as a base.

### Models Merged

The following models were included in the merge:
* [aks1s/13Aks-18](https://huggingface.co/aks1s/13Aks-18)
* [starnet/19star03](https://huggingface.co/starnet/19star03)
* [OwOpeepeepoopoo/ZZZZZsubmission7](https://huggingface.co/OwOpeepeepoopoo/ZZZZZsubmission7)
* [OwOpeepeepoopoo/ZZZZZsubmission5](https://huggingface.co/OwOpeepeepoopoo/ZZZZZsubmission5)
* [starnet/15star03](https://huggingface.co/starnet/15star03)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: irusl/05Ir-4
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: starnet/19star03
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
  - model: starnet/15star03
    parameters:
      density: 0.33
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
  - model: aks1s/13Aks-18
    parameters:
      density: 0.33
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
  - model: OwOpeepeepoopoo/ZZZZZsubmission7
    parameters:
      density: 0.33
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
  - model: OwOpeepeepoopoo/ZZZZZsubmission5
    parameters:
      density: 0.33
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
merge_method: ties
base_model: irusl/05Ir-4
parameters:
  normalize: true
  int8_mask: true
dtype: float16

```