---
base_model:
- Azazelle/Half-NSFW_Noromaid-7b
- mlabonne/NeuralHermes-2.5-Mistral-7B
- NeuralNovel/Panda-7B-v0.1
tags:
- mergekit
- merge
license: openrail
library_name: transformers
pipeline_tag: text-classification
---
# Noromaid-Panda-Mistral-MoE-7B-slerp

# This model is in a testing phase, do not expect anything since I release open llm leaderboard score. 
![intro](screen.png)
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:
* [Azazelle/Half-NSFW_Noromaid-7b](https://huggingface.co/Azazelle/Half-NSFW_Noromaid-7b)
* [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
* [NeuralNovel/Panda-7B-v0.1](https://huggingface.co/NeuralNovel/Panda-7B-v0.1)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: mlabonne/NeuralHermes-2.5-Mistral-7B
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - filter: self_attn
    value: [0.0, 0.5, 0.3, 0.7, 1.0]
  - filter: mlp
    value: [1.0, 0.5, 0.7, 0.3, 0.0]
  - value: 0.5
slices:
- sources:
  - layer_range: [0, 32]
    model: Azazelle/Half-NSFW_Noromaid-7b
  - layer_range: [0, 32]
    model: NeuralNovel/Panda-7B-v0.1
```