README.md

---
base_model:
- grimjim/kukulemon-7B
- Nitral-AI/Kunocchini-7b-128k-test
library_name: transformers
tags:
- mergekit
- merge
- alpaca
- mistral 
license: cc-by-nc-4.0
---
# Kunokukulemonchini-7b

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

Here is an 4.1bpw exl2 quant [Kunokukulemonchini-7b-4.1bpw-exl2](https://huggingface.co/icefog72/Kunokukulemonchini-7b-4.1bpw-exl2) for people like me with 6gb vram.

Thx to Natkituwu for 
- 3.5bpw [Kunokukulemonchini-7b-3.5bpw-exl2](https://huggingface.co/Natkituwu/Kunokukulemonchini-7b-3.5bpw-exl2)
- 5bpw [Kunokukulemonchini-7b-5bpw-exl2](https://huggingface.co/Natkituwu/Kunokukulemonchini-7b-5bpw-exl2)
- 6.5bpw [Kunokukulemonchini-7b-6.5bpw-exl2](https://huggingface.co/Natkituwu/Kunokukulemonchini-7b-6.5bpw-exl2)
- 8bpw [Kunokukulemonchini-7b-8bpw-exl2](https://huggingface.co/Natkituwu/Kunokukulemonchini-7b-8bpw-exl2)

## Merge Details

Slightly edited kukulemon-7B config.json before merge to get at least ~32k context window.

### Merge Method

This model was merged using the SLERP merge method.

### Models Merged

The following models were included in the merge:
* [grimjim/kukulemon-7B](https://huggingface.co/grimjim/kukulemon-7B)
* [Nitral-AI/Kunocchini-7b-128k-test](https://huggingface.co/Nitral-AI/Kunocchini-7b-128k-test)

### Configuration

The following YAML configuration was used to produce this model:

```yaml

slices:
  - sources:
      - model: grimjim/kukulemon-7B
        layer_range: [0, 32]
      - model: Nitral-AI/Kunocchini-7b-128k-test
        layer_range: [0, 32]
merge_method: slerp
base_model: Nitral-AI/Kunocchini-7b-128k-test
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: float16
```