---
base_model:
- allura-org/L3.1-8b-RP-Ink
- squ11z1/Hypnos-i1-8B
- Locutusque/liberalis-cogitator-llama-3.1-8b-dpo
library_name: transformers
tags:
- mergekit
- merge

---
# calm

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 [squ11z1/Hypnos-i1-8B](https://huggingface.co/squ11z1/Hypnos-i1-8B) as a base.

### Models Merged

The following models were included in the merge:
* [allura-org/L3.1-8b-RP-Ink](https://huggingface.co/allura-org/L3.1-8b-RP-Ink)
* [Locutusque/liberalis-cogitator-llama-3.1-8b-dpo](https://huggingface.co/Locutusque/liberalis-cogitator-llama-3.1-8b-dpo)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: squ11z1/Hypnos-i1-8B
chat_template: llama3
dtype: float32
merge_method: sce
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 32]
        model: allura-org/L3.1-8b-RP-Ink
      - layer_range: [0, 32]
        model: Locutusque/liberalis-cogitator-llama-3.1-8b-dpo
      - layer_range: [0, 32]
        model: squ11z1/Hypnos-i1-8B
parameters:
  select_topk: 0.25
tokenizer:
  pad_to_multiple_of: 32
```