README.md

---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- liminerity/1
- Inv/Konstanta-7B
---

# Blur-7b-slerp-v1.44

Blur-7b-slerp-v1.44 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [liminerity/1](https://huggingface.co/liminerity/1)
* [Inv/Konstanta-7B](https://huggingface.co/Inv/Konstanta-7B)

## 🧩 Configuration

```yaml

slices:
  - sources:
      - model: liminerity/1
        layer_range: [0, 32]
      - model: Inv/Konstanta-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/1
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: float16
```