---
base_model:
- DreadPoor/Aurora_faustus-8B-LINEAR
- DreadPoor/Suavemente-8B-Model_Stock
- DreadPoor/Aspire-8B-model_stock
- v000000/L3-8B-Stheno-v3.2-abliterated
- SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B
library_name: transformers
tags:
- mergekit
- merge

---
![image.png](https://huggingface.co/Entropicengine/LatentDream-exp-beta-8b/resolve/main/beta.png)

# LatentDream-exp-β-8b

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 [Linear](https://arxiv.org/abs/2203.05482) merge method.

### Models Merged

The following models were included in the merge:
* [DreadPoor/Aurora_faustus-8B-LINEAR](https://huggingface.co/DreadPoor/Aurora_faustus-8B-LINEAR)
* [DreadPoor/Suavemente-8B-Model_Stock](https://huggingface.co/DreadPoor/Suavemente-8B-Model_Stock)
* [DreadPoor/Aspire-8B-model_stock](https://huggingface.co/DreadPoor/Aspire-8B-model_stock)
* [v000000/L3-8B-Stheno-v3.2-abliterated](https://huggingface.co/v000000/L3-8B-Stheno-v3.2-abliterated)
* [SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B](https://huggingface.co/SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
dtype: float16
merge_method: linear
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 32]
        model: SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B
        parameters:
          weight: 1.0
      - layer_range: [0, 32]
        model: DreadPoor/Suavemente-8B-Model_Stock
        parameters:
          weight: 0.5
      - layer_range: [0, 32]
        model: DreadPoor/Aspire-8B-model_stock
        parameters:
          weight: 0.5
      - layer_range: [0, 32]
        model: DreadPoor/Aurora_faustus-8B-LINEAR
        parameters:
          weight: 0.5
      - layer_range: [0, 32]
        model: v000000/L3-8B-Stheno-v3.2-abliterated
        parameters:
          weight: 0.3
```