README.md

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

# Kunokukulemonchini-7b-6.5bpw-exl2

This is an 6.5 bpw exl2 quant of a merger [icefog72/Kunokukulemonchini-7b](https://huggingface.co/icefog72/Kunokukulemonchini-7b).

With a 4060 8GB. i am able to run this at 16K context at 8bit cache. and 24K context with 4bit cache.

## 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/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
```