---
library_name: transformers
tags:
- mergekit
- merge
- mistral
---

# Tips

I haven't done any rigorous testing on this model, although it can become extremely unhinged depending on your character card.

SillyTavern [presets](https://huggingface.co/Virt-io/Nina-7B/tree/main/presets) included.

___

# Nina-7B

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 [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [Test157t/Mika-Longtext-7b](https://huggingface.co/Test157t/Mika-Longtext-7b) as a base.

### Models Merged

The following models were included in the merge:
* Mergekit/SmartyPants-Cerebrum-FC
* [Nitral-AI/Mika-Longtext-7b](https://huggingface.co/Nitral-AI/Mika-Longtext-7b)
* [tavtav/eros-7b-test](https://huggingface.co/tavtav/eros-7b-test)
* [ChaoticNeutrals/BuRP_7B](https://huggingface.co/ChaoticNeutrals/BuRP_7B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Test157t/Mika-Longtext-7b
    parameters:
      weight: 1.0
  - model: ChaoticNeutrals/BuRP_7B
    parameters:
      weight: 0.75
  - model: Mergekit/SmartyPants-Cerebrum-FC
    parameters:
      weight: 0.70
  - model: tavtav/eros-7b-test
    parameters:
      weight: 0.20
merge_method: task_arithmetic
base_model: Test157t/Mika-Longtext-7b
parameters:
  normalize: true
  int8_mask: true
dtype: float16
```