README.md

metadata

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, 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

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
• NousResearch/Nous-Hermes-2-Mistral-7B-DPO

Configuration

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