---
base_model:
- PocketDoc/Dans-PersonalityEngine-V1.2.0-24b
- ReadyArt/Forgotten-Safeword-24B-v4.0
- arcee-ai/Arcee-Blitz
- lars1234/Mistral-Small-24B-Instruct-2501-writer
library_name: transformers
tags:
- mergekit
- merge
- chatml
---
![image/png](https://huggingface.co/yamatazen/EsotericKnowledge-24B/resolve/main/EsotericKnowledge-24B.png?download=true)
This is my first 24B 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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [arcee-ai/Arcee-Blitz](https://huggingface.co/arcee-ai/Arcee-Blitz) as a base.

### Models Merged

The following models were included in the merge:
* [PocketDoc/Dans-PersonalityEngine-V1.2.0-24b](https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.2.0-24b)
* [ReadyArt/Forgotten-Safeword-24B-v4.0](https://huggingface.co/ReadyArt/Forgotten-Safeword-24B-v4.0)
* [lars1234/Mistral-Small-24B-Instruct-2501-writer](https://huggingface.co/lars1234/Mistral-Small-24B-Instruct-2501-writer)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: arcee-ai/Arcee-Blitz
models:
  - model: ReadyArt/Forgotten-Safeword-24B-v4.0
    parameters:
      density: 0.75
      weight: 0.8
  - model: lars1234/Mistral-Small-24B-Instruct-2501-writer
    parameters:
      density: 0.6
      weight: 0.5
  - model: PocketDoc/Dans-PersonalityEngine-V1.2.0-24b
    parameters:
      density: 0.5
      weight: 0.3
merge_method: ties
dtype: bfloat16
parameters:
  normalize: true
tokenizer:
  source: union
```