---
base_model:
- TheDrummer/Cydonia-22B-v1.1
- nbeerbower/Mistral-Small-Drummer-22B
- gghfez/SeminalRP-22b
- ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
library_name: transformers
tags:
- mergekit
- merge

---
## Karasik 0.2

### Overview

Somewhat experimental merge of some Mistral Small models. 

### Quants

[Static](https://huggingface.co./mradermacher/Karasik-22B-v0.2-GGUF)

[Imatrix](https://huggingface.co./mradermacher/Karasik-22B-v0.2-i1-GGUF)

## Merge Details
### Merge Method

This model was merged using the della_linear merge method using [ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1](https://huggingface.co./ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1) as a base.

### Models Merged

The following models were included in the merge:
* [TheDrummer/Cydonia-22B-v1.1](https://huggingface.co./TheDrummer/Cydonia-22B-v1.1)
* [nbeerbower/Mistral-Small-Drummer-22B](https://huggingface.co./nbeerbower/Mistral-Small-Drummer-22B)
* [gghfez/SeminalRP-22b](https://huggingface.co./gghfez/SeminalRP-22b)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
parameters:
  epsilon: 0.04
  lambda: 1.05
  int8_mask: true
  rescale: true
  normalize: false
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
models:
  - model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
    parameters:
      weight: [0.2, 0.3, 0.2, 0.3, 0.2]
      density: [0.45, 0.55, 0.45, 0.55, 0.45]
  - model: gghfez/SeminalRP-22b
    parameters:
      weight: [0.01768, -0.01675, 0.01285, -0.01696, 0.01421]
      density: [0.6, 0.4, 0.5, 0.4, 0.6]
  - model: TheDrummer/Cydonia-22B-v1.1
    parameters:
      weight: [0.208, 0.139, 0.139, 0.139, 0.208]
      density: [0.7]
  - model: nbeerbower/Mistral-Small-Drummer-22B
    parameters:
      weight: [0.33]
      density: [0.45, 0.55, 0.45, 0.55, 0.45]
```