---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- ZeroXClem/Llama3.1-Hermes3-SuperNova-8B-L3.1-Purosani-2-8B
- Casual-Autopsy/L3-bluuwhale-SAO-MIX-8B-V1_fp32-merge-calc
---

# ZeroXClem/L3-SAO-Mix-SuperHermes-NovaPurosani-8B

ZeroXClem/L3-SAO-Mix-SuperHermes-NovaPurosani-8B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [ZeroXClem/Llama3.1-Hermes3-SuperNova-8B-L3.1-Purosani-2-8B](https://huggingface.co/ZeroXClem/Llama3.1-Hermes3-SuperNova-8B-L3.1-Purosani-2-8B)
* [Casual-Autopsy/L3-bluuwhale-SAO-MIX-8B-V1_fp32-merge-calc](https://huggingface.co/Casual-Autopsy/L3-bluuwhale-SAO-MIX-8B-V1_fp32-merge-calc)

## 🧩 Configuration

```yaml
merge_method: della_linear
dtype: bfloat16
parameters:
  epsilon: 0.1
  lambda: 1.0
  int8_mask: true
  normalize: true

# Base model
base_model: ZeroXClem/Llama3.1-Hermes3-SuperNova-8B-L3.1-Purosani-2-8B

# Models to merge, including the base model itself again
models:
  - model: ZeroXClem/Llama3.1-Hermes3-SuperNova-8B-L3.1-Purosani-2-8B
    parameters:
      weight: 1
      density: 0.5
  - model: Casual-Autopsy/L3-bluuwhale-SAO-MIX-8B-V1_fp32-merge-calc
    parameters:
      weight: 1
      density: 0.55

```