---
base_model:
- ABX-AI/Cerebral-Infinity-7B
- ABX-AI/Spicy-Laymonade-7B
library_name: transformers
tags:
- mergekit
- merge
- not-for-all-audiences
---
# GGUF / IQ / Imatrix for [Cosmic-Citrus-9B](https://huggingface.co/ABX-AI/Cosmic-Citrus-9B)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d936ad52eca001fdcd3245/mm8eJBytwElxWw_V1voDW.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 custom kink.


# Cosmic-Citrus-9B

Another attempt at merging Cerebrum, InfinityRP, LemonadeRP, and Laymonade, all already merged in my previous merges, now into a 9B containing TheSpice.

So far in my tests, it seems to follow my cards in intriguing way, using refined language, with more consideration of what the prompt is saying.

In fact, I'm quite positively surprised as the creativity surpassed my expectations. It's quickly becoming a favorite to use for me.

## Merge Details

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

### Merge Method

This model was merged using the passthrough merge method.

### Models Merged

The following models were included in the merge:
* [ABX-AI/Cerebral-Infinity-7B](https://huggingface.co/ABX-AI/Cerebral-Infinity-7B)
* [ABX-AI/Spicy-Laymonade-7B](https://huggingface.co/ABX-AI/Spicy-Laymonade-7B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
  - sources:
      - model: ABX-AI/Cerebral-Infinity-7B
        layer_range: [0, 20]
  - sources:
      - model: ABX-AI/Spicy-Laymonade-7B
        layer_range: [12, 32]
merge_method: passthrough
dtype: float16

```