README.md

---
base_model:
- Kaoeiri/MS-Inky-2409-22B
- invisietch/MiS-Firefly-v0.2-22B
- Kaoeiri/MS_a-coolyte-2409-22B
- DigitalSouls/BlackSheep-DigitalSoul-22B
- Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-8
- Kaoeiri/MS_fujin-2409-22B
- Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small
- Darkknight535/MS-Moonlight-22B-v3
- Kaoeiri/MS_Moingooistral-2409-22B
- InferenceIllusionist/SorcererLM-22B
- spow12/ChatWaifu_v2.0_22B
- crestf411/MS-sunfall-v0.7.0
- Envoid/Mistral-Small-NovusKyver
- ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
- unsloth/Mistral-Small-Instruct-2409
- Saxo/Linkbricks-Horizon-AI-Japanese-Superb-V1-22B
- allura-org/MS-Meadowlark-22B
- qingy2024/MwM-22B-Instruct
- TheDrummer/Cydonia-22B-v1.3
- Kaoeiri/MS_dampf-2409-22B
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](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [unsloth/Mistral-Small-Instruct-2409](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409) as a base.

### Models Merged

The following models were included in the merge:
* [Kaoeiri/MS-Inky-2409-22B](https://huggingface.co/Kaoeiri/MS-Inky-2409-22B)
* [invisietch/MiS-Firefly-v0.2-22B](https://huggingface.co/invisietch/MiS-Firefly-v0.2-22B)
* [Kaoeiri/MS_a-coolyte-2409-22B](https://huggingface.co/Kaoeiri/MS_a-coolyte-2409-22B)
* [DigitalSouls/BlackSheep-DigitalSoul-22B](https://huggingface.co/DigitalSouls/BlackSheep-DigitalSoul-22B)
* [Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-8](https://huggingface.co/Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-8)
* [Kaoeiri/MS_fujin-2409-22B](https://huggingface.co/Kaoeiri/MS_fujin-2409-22B)
* [Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small](https://huggingface.co/Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small)
* [Darkknight535/MS-Moonlight-22B-v3](https://huggingface.co/Darkknight535/MS-Moonlight-22B-v3)
* [Kaoeiri/MS_Moingooistral-2409-22B](https://huggingface.co/Kaoeiri/MS_Moingooistral-2409-22B)
* [InferenceIllusionist/SorcererLM-22B](https://huggingface.co/InferenceIllusionist/SorcererLM-22B)
* [spow12/ChatWaifu_v2.0_22B](https://huggingface.co/spow12/ChatWaifu_v2.0_22B)
* [crestf411/MS-sunfall-v0.7.0](https://huggingface.co/crestf411/MS-sunfall-v0.7.0)
* [Envoid/Mistral-Small-NovusKyver](https://huggingface.co/Envoid/Mistral-Small-NovusKyver)
* [ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1](https://huggingface.co/ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1)
* [Saxo/Linkbricks-Horizon-AI-Japanese-Superb-V1-22B](https://huggingface.co/Saxo/Linkbricks-Horizon-AI-Japanese-Superb-V1-22B)
* [allura-org/MS-Meadowlark-22B](https://huggingface.co/allura-org/MS-Meadowlark-22B)
* [qingy2024/MwM-22B-Instruct](https://huggingface.co/qingy2024/MwM-22B-Instruct)
* [TheDrummer/Cydonia-22B-v1.3](https://huggingface.co/TheDrummer/Cydonia-22B-v1.3)
* [Kaoeiri/MS_dampf-2409-22B](https://huggingface.co/Kaoeiri/MS_dampf-2409-22B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  # Obedience and Strong Replies
  - model: qingy2024/MwM-22B-Instruct
    parameters:
      weight: 1.2
      density: 0.8
  - model: DigitalSouls/BlackSheep-DigitalSoul-22B
    parameters:
      weight: 0.8
      density: 0.85
  - model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
    parameters:
      weight: 0.7
      density: 0.85

  # RP and Storytelling
  - model: Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-8
    parameters:
      weight: 0.8
      density: 0.75
  - model: TheDrummer/Cydonia-22B-v1.3
    parameters:
      weight: 0.5
      density: 0.7
  - model: spow12/ChatWaifu_v2.0_22B
    parameters:
      weight: 0.5
      density: 0.7
  - model: Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small
    parameters:
      weight: 0.5
      density: 0.7

  # Background and Additional Features
  - model: Darkknight535/MS-Moonlight-22B-v3
    parameters:
      weight: 0.3
      density: 0.7
  - model: InferenceIllusionist/SorcererLM-22B
    parameters:
      weight: 0.3
      density: 0.7
  - model: Envoid/Mistral-Small-NovusKyver
    parameters:
      weight: 0.3
      density: 0.7
  - model: crestf411/MS-sunfall-v0.7.0
    parameters:
      weight: 0.3
      density: 0.7
  - model: Kaoeiri/MS_a-coolyte-2409-22B
    parameters:
      weight: 0.3
      density: 0.7
  - model: invisietch/MiS-Firefly-v0.2-22B
    parameters:
      weight: 0.3
      density: 0.7
  - model: Kaoeiri/MS_fujin-2409-22B
    parameters:
      weight: 0.3
      density: 0.7
  - model: Kaoeiri/MS_dampf-2409-22B
    parameters:
      weight: 0.3
      density: 0.7
  - model: allura-org/MS-Meadowlark-22B
    parameters:
      weight: 0.3
      density: 0.7
  - model: Saxo/Linkbricks-Horizon-AI-Japanese-Superb-V1-22B
    parameters:
      weight: 0.3
      density: 0.7
  - model: Kaoeiri/MS_Moingooistral-2409-22B
    parameters:
      weight: 0.3
      density: 0.7
  - model: Kaoeiri/MS-Inky-2409-22B
    parameters:
      weight: 0.3
      density: 0.7

merge_method: dare_ties
base_model: unsloth/Mistral-Small-Instruct-2409
parameters:
  density: 0.90
  epsilon: 0.08
  lambda: 1.18
  normalize: true
dtype: bfloat16
```