---
base_model:
- DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS
- mergekit-community/MN-Sappho-j-12B
- nbeerbower/mistral-nemo-wissenschaft-12B
- mergekit-community/MN-Hekate-Nykhia-17B
- mergekit-community/MN-Sappho-g3-12B
- jtatman/mistral_nemo_12b_reasoning_psychology_lora
- Nitral-Archive/Diogenes-12B
- mistralai/Mistral-Nemo-Base-2407
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 [mergekit-community/MN-Hekate-Nykhia-17B](https://huggingface.co/mergekit-community/MN-Hekate-Nykhia-17B) as a base.

### Models Merged

The following models were included in the merge:
* [DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS](https://huggingface.co/DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS)
* [mergekit-community/MN-Sappho-j-12B](https://huggingface.co/mergekit-community/MN-Sappho-j-12B)
* [nbeerbower/mistral-nemo-wissenschaft-12B](https://huggingface.co/nbeerbower/mistral-nemo-wissenschaft-12B)
* [mergekit-community/MN-Sappho-g3-12B](https://huggingface.co/mergekit-community/MN-Sappho-g3-12B) + [jtatman/mistral_nemo_12b_reasoning_psychology_lora](https://huggingface.co/jtatman/mistral_nemo_12b_reasoning_psychology_lora)
* [Nitral-Archive/Diogenes-12B](https://huggingface.co/Nitral-Archive/Diogenes-12B)
* [mistralai/Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: mergekit-community/MN-Hekate-Nykhia-17B
slices:
  - sources:
    - model: mergekit-community/MN-Hekate-Nykhia-17B
      layer_range: [0, 20]

  - sources:
    - model: mergekit-community/MN-Hekate-Nykhia-17B
      layer_range: [20, 36]
      parameters:
        weight: [0.5, 0.25]
    - model: mistralai/Mistral-Nemo-Base-2407
      layer_range: [16, 32]
      parameters:
        weight: [2, 1]
    - model: Nitral-Archive/Diogenes-12B
      layer_range: [16, 32]
      parameters:
        weight: [1, 2]
    - model: mergekit-community/MN-Sappho-g3-12B+jtatman/mistral_nemo_12b_reasoning_psychology_lora
      layer_range: [16, 32]
      parameters:
        weight: [1.5, 1.49, 1.46, 1.4, 1.33, 1.25, 1.15, 1.05, 1]
    - model: nbeerbower/mistral-nemo-wissenschaft-12B
      layer_range: [16, 32]
      parameters:
        weight: [1.5, 1.49, 1.46, 1.4, 1.33, 1.25, 1.15, 1.05, 1]
    - model: mergekit-community/MN-Sappho-j-12B
      layer_range: [16, 32]
      parameters:
        weight: [1.0, 1.1, 1.2, 1.29, 1.37, 1.43, 1.48, 1.5, 1.5]
    - model: DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS
      layer_range: [16, 32]
      parameters:
        weight: [1.0, 1.1, 1.2, 1.29, 1.37, 1.43, 1.48, 1.5, 1.5]

  - sources:
    - model: mergekit-community/MN-Hekate-Nykhia-17B
      layer_range: [36, 56]

tokenizer:
  source: union
  tokens:
    "[INST]":
      source: mergekit-community/MN-Hekate-Nykhia-17B
      force: true
    "[/INST]":
      source: mergekit-community/MN-Hekate-Nykhia-17B
      force: true
    "<|im_start|>":
      source: mergekit-community/MN-Hekate-Nykhia-17B
      force: true
    "<|im_end|>":
      source: mergekit-community/MN-Hekate-Nykhia-17B
      force: true

```