---
base_model:
- yamatazen/Himeyuri-Magnum-12B-v2
- HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
- PocketDoc/Dans-PersonalityEngine-V1.1.0-12b
- EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math
- yamatazen/LoyalMaid-12B
- inflatebot/MN-12B-Mag-Mell-R1
library_name: transformers
tags:
- mergekit
- merge
- chatml
language:
- en
- ja
---
![image/png](https://huggingface.co/yamatazen/ElvenMaid-12B-v2/resolve/main/ElvenMaid-12B-v2.png?download=true)
This is a ChatML model.
# 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 [PocketDoc/Dans-PersonalityEngine-V1.1.0-12b](https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.1.0-12b) as a base.

### Models Merged

The following models were included in the merge:
* [yamatazen/Himeyuri-Magnum-12B-v2](https://huggingface.co/yamatazen/Himeyuri-Magnum-12B-v2)
* [HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407](https://huggingface.co/HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407)
* [EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math](https://huggingface.co/EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math)
* [yamatazen/LoyalMaid-12B](https://huggingface.co/yamatazen/LoyalMaid-12B)
* [inflatebot/MN-12B-Mag-Mell-R1](https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: PocketDoc/Dans-PersonalityEngine-V1.1.0-12b
models:
  - model: yamatazen/Himeyuri-Magnum-12B-v2
    parameters:
      density: 1.0
      weight: 1.0
  - model: yamatazen/LoyalMaid-12B
    parameters:
      density: 0.75
      weight: 1.0
  - model: inflatebot/MN-12B-Mag-Mell-R1
    parameters:
      density: 0.5
      weight: 1.0
  - model: EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math
    parameters:
      density: 0.3
      weight: 1.0
  - model: HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
    parameters:
      density: 0.25
      weight: 1.0
merge_method: ties
dtype: bfloat16
parameters:
  normalize: true
```