README.md

---
license: apache-2.0
tags:
- merge
- mergekit
- meta-math/MetaMath-Mistral-7B
- beowolx/MistralHermes-CodePro-7B-v1
---

# 3_alt_merges_exp_1-2

3_alt_merges_exp_1-2 is a merged model generated for Model Kinship experiments, originating from mistralai/Mistral-7B-v0.1
* [meta-math/MetaMath-Mistral-7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B)
* [beowolx/MistralHermes-CodePro-7B-v1](https://huggingface.co/beowolx/MistralHermes-CodePro-7B-v1)

## 🧩 Configuration

```yaml
slices:
  - sources:
      - model: meta-math/MetaMath-Mistral-7B
        layer_range: [0, 32]
      - model: beowolx/MistralHermes-CodePro-7B-v1
        layer_range: [0, 32]
merge_method: slerp
base_model: meta-math/MetaMath-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
```