README.md

---
license: apache-2.0
base_model:
- teknium/OpenHermes-2.5-Mistral-7B
- NousResearch/Nous-Hermes-2-Mistral-7B-DPO
tags:
- merge
- mergekit
- lazymergekit
- mistral
- hermes
- dpo
---
# SUONG-2

This is a merge of two leading Hermes models created using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing), combining OpenHermes's robust capabilities with Nous-Hermes-DPO's refined instruction following.

## About Me
I'm David Soeiro-Vuong, a third-year Computer Science student working as an apprentice at TW3 Partners, a company specialized in Generative AI. Passionate about artificial intelligence and language models optimization, I focus on creating efficient model merges that balance performance and capabilities.

🔗 [Connect with me on LinkedIn](https://www.linkedin.com/in/david-soeiro-vuong-a28b582ba/)

## Merge Details
### Merge Method
This model uses SLERP (Spherical Linear Interpolation) with carefully tuned parameters:
- Progressive attention layer fusion patterns
- Balanced MLP layer transitions
- bfloat16 format for efficient memory usage
- Full layer utilization for maximum capability retention

### Models Merged
* [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
* [NousResearch/Nous-Hermes-2-Mistral-7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO)

### Configuration
```yaml
slices:
  - sources:
      - model: teknium/OpenHermes-2.5-Mistral-7B
        layer_range: [0, 32]
      - model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
        layer_range: [0, 32]
merge_method: slerp
base_model: teknium/OpenHermes-2.5-Mistral-7B
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