---
base_model:
- unsloth/Mistral-Small-24B-Instruct-2501
- ReadyArt/Forgotten-Safeword-24B-v4.0
- TroyDoesAI/BlackSheep-24B
library_name: transformers
tags:
- mergekit
- merge

---
# Capybara_24B_v2

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 TIES](https://arxiv.org/abs/2311.03099) merge method using [unsloth/Mistral-Small-24B-Instruct-2501](https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501) as a base.

### Models Merged

The following models were included in the merge:
* [ReadyArt/Forgotten-Safeword-24B-v4.0](https://huggingface.co/ReadyArt/Forgotten-Safeword-24B-v4.0)
* [TroyDoesAI/BlackSheep-24B](https://huggingface.co/TroyDoesAI/BlackSheep-24B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: ReadyArt/Forgotten-Safeword-24B-v4.0
    parameters:
      weight: 0.3
      density: 0.35
  - model: TroyDoesAI/BlackSheep-24B
    parameters:
      weight: 0.4
      density: 0.35
  - model: unsloth/Mistral-Small-24B-Instruct-2501
    parameters:
      weight: 0.3
      density: 0.35
merge_method: dare_ties
base_model: unsloth/Mistral-Small-24B-Instruct-2501
parameters:
  normalize: true
  int8_mask: true
  temperature: 1.5
tokenizer_source: union
dtype: bfloat16
chat_template: auto
```