---
base_model:
- collinzrj/DeepSeek-R1-Distill-Llama-8B-abliterate
- prithivMLmods/Llama-8B-Distill-CoT
- jaspionjader/Kosmos-EVAA-immersive-mix-v45.1-8B
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 [jaspionjader/Kosmos-EVAA-immersive-mix-v45.1-8B](https://huggingface.co/jaspionjader/Kosmos-EVAA-immersive-mix-v45.1-8B) as a base.

### Models Merged

The following models were included in the merge:
* [collinzrj/DeepSeek-R1-Distill-Llama-8B-abliterate](https://huggingface.co/collinzrj/DeepSeek-R1-Distill-Llama-8B-abliterate)
* [prithivMLmods/Llama-8B-Distill-CoT](https://huggingface.co/prithivMLmods/Llama-8B-Distill-CoT)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: jaspionjader/Kosmos-EVAA-immersive-mix-v45.1-8B
  - model: prithivMLmods/Llama-8B-Distill-CoT
  - model: collinzrj/DeepSeek-R1-Distill-Llama-8B-abliterate
merge_method: sce
base_model: jaspionjader/Kosmos-EVAA-immersive-mix-v45.1-8B
parameters:
  select_topk: 0.07
dtype: bfloat16
```