---
base_model:
- mergekit-community/MN-Hecate-Chthonia-12B
- mergekit-community/MN-Chthonia-12B
- HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
- XeroCodes/aurora-12b
- yamatazen/EtherealAurora-12B-v3
- mergekit-community/MN-Nyx-Chthonia-12B
- mistralai/Mistral-Nemo-Instruct-2407
- mergekit-community/MN-Ephemeros-12B
- mergekit-community/MN-Anathema-12B
- jtatman/mistral_nemo_12b_reasoning_psychology_lora
- nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2
- jtatman/mistral_nemo_12b_reasoning_psychology_lora
library_name: transformers
tags:
- mergekit
- 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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) as a base.

### Models Merged

The following models were included in the merge:
* [mergekit-community/MN-Hecate-Chthonia-12B](https://huggingface.co/mergekit-community/MN-Hecate-Chthonia-12B)
* [mergekit-community/MN-Chthonia-12B](https://huggingface.co/mergekit-community/MN-Chthonia-12B)
* [HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407](https://huggingface.co/HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407) + [XeroCodes/aurora-12b](https://huggingface.co/XeroCodes/aurora-12b)
* [yamatazen/EtherealAurora-12B-v3](https://huggingface.co/yamatazen/EtherealAurora-12B-v3)
* [mergekit-community/MN-Nyx-Chthonia-12B](https://huggingface.co/mergekit-community/MN-Nyx-Chthonia-12B)
* [mergekit-community/MN-Ephemeros-12B](https://huggingface.co/mergekit-community/MN-Ephemeros-12B)
* [mergekit-community/MN-Anathema-12B](https://huggingface.co/mergekit-community/MN-Anathema-12B) + [jtatman/mistral_nemo_12b_reasoning_psychology_lora](https://huggingface.co/jtatman/mistral_nemo_12b_reasoning_psychology_lora)
* [nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2](https://huggingface.co/nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2) + [jtatman/mistral_nemo_12b_reasoning_psychology_lora](https://huggingface.co/jtatman/mistral_nemo_12b_reasoning_psychology_lora)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: mistralai/Mistral-Nemo-Instruct-2407
models:
  - model: mergekit-community/MN-Anathema-12B+jtatman/mistral_nemo_12b_reasoning_psychology_lora
  - model: mergekit-community/MN-Chthonia-12B
    parameters:
      weight: 1.2
  - model: mergekit-community/MN-Ephemeros-12B
    parameters:
      weight: 1.1
  - model: mergekit-community/MN-Hecate-Chthonia-12B
    parameters:
      weight: 0.6
  - model: mergekit-community/MN-Nyx-Chthonia-12B
    parameters:
      weight: 1.3
  - model: nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2+jtatman/mistral_nemo_12b_reasoning_psychology_lora
  - model: HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407+XeroCodes/aurora-12b
  - model: yamatazen/EtherealAurora-12B-v3

chat_template: chatml
tokenizer:
  source: union
  tokens:
    "[INST]":
      source: mistralai/Mistral-Nemo-Instruct-2407
      force: true
    "[/INST]":
      source: mistralai/Mistral-Nemo-Instruct-2407
      force: true
    "<|im_start|>":
      source: yamatazen/EtherealAurora-12B-v3
      force: true
    "<|im_end|>":
      source: yamatazen/EtherealAurora-12B-v3
      force: true
```