---
base_model:
- TheDrummer/Fallen-Llama-3.3-R1-70B-v1
- Mawdistical/Vulpine-Seduction-70B
- SicariusSicariiStuff/Negative_LLAMA_70B
- TareksLab/Transgression-LLaMa-70B
library_name: transformers
tags:
- mergekit
- merge

---
# merge

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 [SCE](https://arxiv.org/abs/2408.07990) merge method using [SicariusSicariiStuff/Negative_LLAMA_70B](https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B) as a base.

### Models Merged

The following models were included in the merge:
* [TheDrummer/Fallen-Llama-3.3-R1-70B-v1](https://huggingface.co/TheDrummer/Fallen-Llama-3.3-R1-70B-v1)
* [Mawdistical/Vulpine-Seduction-70B](https://huggingface.co/Mawdistical/Vulpine-Seduction-70B)
* [TareksLab/Transgression-LLaMa-70B](https://huggingface.co/TareksLab/Transgression-LLaMa-70B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Mawdistical/Vulpine-Seduction-70B
    parameters:
      select_topk: 0.8
  - model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
    parameters:
      select_topk: 0.8
  - model: TareksLab/Transgression-LLaMa-70B
    parameters:
      select_topk: 0.8
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
    parameters:
      select_topk: 0.8
base_model: SicariusSicariiStuff/Negative_LLAMA_70B
merge_method: sce
parameters:
  int8_mask: true
tokenizer:
  source: Mawdistical/Vulpine-Seduction-70B
chat_template: llama3
dtype: float32
out_dtype: bfloat16
```