---
base_model:
- anthracite-org/magnum-v2.5-12b-kto
- nbeerbower/mistral-nemo-wissenschaft-12B
- EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math
library_name: transformers
tags:
- mergekit
- merge

---
# merge

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Ollama template

```
TEMPLATE """{{ if .System }}[INST]system
{{ .System }}[\INST]
{{ end }}{{ if .Prompt }}[INST]user
{{ .Prompt }}[\INST]
{{ end }}[INST]assistant
{{ .Response }}[\INST]</s>
"""
PARAMETER stop "</s>"
PARAMETER stop "[\INST]"
```

## Merge Details
### Merge Method

This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [anthracite-org/magnum-v2.5-12b-kto](https://huggingface.co/anthracite-org/magnum-v2.5-12b-kto) as a base.

### Models Merged

The following models were included in the merge:
* [nbeerbower/mistral-nemo-wissenschaft-12B](https://huggingface.co/nbeerbower/mistral-nemo-wissenschaft-12B)
* [EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math](https://huggingface.co/EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: anthracite-org/magnum-v2.5-12b-kto
    #no parameters necessary for base model
  - model: EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math
    parameters:
      density: 0.5
      weight: 0.5
  - model: nbeerbower/mistral-nemo-wissenschaft-12B
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: anthracite-org/magnum-v2.5-12b-kto
parameters:
  normalize: false
  int8_mask: true
dtype: float16
```