README.md

---
base_model:
- TheDrummer/Cydonia-22B-v1.2
- anthracite-org/magnum-v4-22b
library_name: transformers
tags:
- mergekit
- merge
license: other
license_name: mrl
inference: false
license_link: https://mistral.ai/licenses/MRL-0.1.md

---
# Do not quant this model.

![Not Horny Enough](Cydonia-v1.2-Magnum-v4-22B.png)

# Do not quant this model.

It's already available.

- GGUF (static): [mradermacher/Cydonia-v1.2-magnum-v4-22B-GGUF](https://huggingface.co/mradermacher/Cydonia-v1.2-magnum-v4-22B-GGUF)
- GGUF (weighted/imatrix): [mradermacher/Cydonia-v1.2-magnum-v4-22B-i1-GGUF](https://huggingface.co/mradermacher/Cydonia-v1.2-magnum-v4-22B-i1-GGUF)

Unfortunately, I deleted the original cooked model and was already on the way to be quanted. I recooked it again from memory for archive, just in case someone needs it.

# The Drummer becomes hornier

Recipe based on [MarsupialAI/Monstral-123B](https://huggingface.co/MarsupialAI/Monstral-123B). It should work since it's the same Mistral, TheDrummer and MarsupialAI, right?

This is a merge of pre-trained language models created using [mergekit](https://github.com/arcee-ai/mergekit).

## Merge Details
### Merge Method

This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [TheDrummer/Cydonia-22B-v1.2](https://huggingface.co/TheDrummer/Cydonia-22B-v1.2) as a base.

### Models Merged

The following models were included in the merge:
* [anthracite-org/magnum-v4-22b](https://huggingface.co/anthracite-org/magnum-v4-22b)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: TheDrummer/Cydonia-22B-v1.2
    parameters:
      weight: 0.5
  - model: anthracite-org/magnum-v4-22b
    parameters:
      weight: 0.5
merge_method: task_arithmetic
base_model: TheDrummer/Cydonia-22B-v1.2
dtype: float16
```