---
base_model:
- NeverSleep/Noromaid-7B-0.4-DPO
- localfultonextractor/Erosumika-7B-v2
library_name: transformers
tags:
- mergekit
- merge
- mistral
- not-for-all-audiences
---

GGUF-IQ-Imatrix for [Norosumika-7B](https://huggingface.co/ABX-AI/Norosumika-7B)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d936ad52eca001fdcd3245/a4qqO7m_X44ufGFrvsj-N.png)

**Why Importance Matrix?**

**Importance Matrix**, at least based on my testing, has shown to improve the output and performance of "IQ"-type quantizations, where the compression becomes quite heavy.
The **Imatrix** performs a calibration, using a provided dataset. Testing has shown that semi-randomized data can help perserve more important segments as the compression is applied.

Related discussions in Github:
[[1]](https://github.com/ggerganov/llama.cpp/discussions/5006) [[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)

The imatrix.txt file that I used contains general, semi-random data, with some added extra kink.

# Norosumika-7B

This model is intended for role-playing and storywriting purposes.

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 SLERP merge method.

### Models Merged

The following models were included in the merge:
* [NeverSleep/Noromaid-7B-0.4-DPO](https://huggingface.co/NeverSleep/Noromaid-7B-0.4-DPO)
* [localfultonextractor/Erosumika-7B-v2](https://huggingface.co/localfultonextractor/Erosumika-7B-v2)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
  - sources:
      - model: NeverSleep/Noromaid-7B-0.4-DPO
        layer_range: [0, 32]
      - model: localfultonextractor/Erosumika-7B-v2
        layer_range: [0, 32]
merge_method: slerp
base_model: localfultonextractor/Erosumika-7B-v2
parameters:
  t:
    - filter: self_attn
      value: [0.5, 0.5, 0.5, 0.5, 0.5]
    - filter: mlp
      value: [0.5, 0.5, 0.5, 0.5, 0.5]
    - value: 0.5
dtype: bfloat16
```