README.md

---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- catrinbaze/llama-refueled-merge
- Locutusque/Llama-3-Orca-1.0-8B
---

# llama3_refuled_orca_slerp

llama3_refuled_orca_slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [catrinbaze/llama-refueled-merge](https://huggingface.co/catrinbaze/llama-refueled-merge)
* [Locutusque/Llama-3-Orca-1.0-8B](https://huggingface.co/Locutusque/Llama-3-Orca-1.0-8B)

## 🧩 Configuration

```yaml
slices:
  - sources:
      - model: catrinbaze/llama-refueled-merge
        layer_range: [0, 32]
      - model: Locutusque/Llama-3-Orca-1.0-8B
        layer_range: [0, 32]
merge_method: slerp
base_model: catrinbaze/llama-refueled-merge
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16
```