MixSwap/README.md

---
base_model:
- cognitivecomputations/dolphin-2.2.1-mistral-7b
- l3utterfly/mistral-7b-v0.1-layla-v4-chatml
- teknium/Mistral-Trismegistus-7B
- Aryanne/Open-StarLake-Swap-7B
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
---
# MixSwap

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit), but my branch was used
 [here](https://github.com/Ar57m/mergekit/tree/swapping) 

## Merge Details
### Merge Method

This model was merged using the task_swapping merge method using [Aryanne/Open-StarLake-Swap-7B](https://huggingface.co/Aryanne/Open-StarLake-Swap-7B) as a base.

### Models Merged

The following models were included in the merge:
* [cognitivecomputations/dolphin-2.2.1-mistral-7b](https://huggingface.co/cognitivecomputations/dolphin-2.2.1-mistral-7b)
* [teknium/Mistral-Trismegistus-7B](https://huggingface.co/teknium/Mistral-Trismegistus-7B)
* [l3utterfly/mistral-7b-v0.1-layla-v4-chatml](https://huggingface.co/l3utterfly/mistral-7b-v0.1-layla-v4-chatml)

### Prompt Format:
I prefer using this way, which seems to work.

### Example using Koboldcpp:

Start Seq.: 
```
\nYour_name: 
```

End Seq.:
```
\nCharacter_name: 
```

In Memory
```
### Instruction:
Character description.

Generate a endless verbose(very descriptive) role-play conversation with Character_name.

### Response:
Your_name: how are you doing babe? *Your_name approaches Character_name and kisses her in the lips*
Character_name: I'm fine, it's been an weird day. *Character_name blushes and hugs Your_name with love*
```



### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model:
  model:
    path: Aryanne/Open-StarLake-Swap-7B
dtype: bfloat16
merge_method: task_swapping
slices:
- sources:
  - layer_range: [0, 32]
    model:
      model:
        path: l3utterfly/mistral-7b-v0.1-layla-v4-chatml
    parameters:
      diagonal_offset: 4.0
      random_mask: 0.1
      random_mask_seed: 1956557.0
      weight: 0.4
  - layer_range: [0, 32]
    model:
      model:
        path: cognitivecomputations/dolphin-2.2.1-mistral-7b
    parameters:
      diagonal_offset: 4.0
      random_mask: 0.1
      random_mask_seed: 18019.0
      weight: 0.333
  - layer_range: [0, 32]
    model:
      model:
        path: teknium/Mistral-Trismegistus-7B
    parameters:
      diagonal_offset: 4.0
      random_mask: 0.05
      random_mask_seed: 666666.0
      weight: 0.5
  - layer_range: [0, 32]
    model:
      model:
        path: Aryanne/Open-StarLake-Swap-7B
```