---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- cognitivecomputations/Dolphin-2.9.1-Phi-3-Kensho-4.5B-abliterated-v3
- bunnycore/HyperLlama-3.1-8B
---

# LLamaPhi3

LLamaPhi3 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [cognitivecomputations/Dolphin-2.9.1-Phi-3-Kensho-4.5B-abliterated-v3](https://huggingface.co/cognitivecomputations/Dolphin-2.9.1-Phi-3-Kensho-4.5B-abliterated-v3)
* [bunnycore/HyperLlama-3.1-8B](https://huggingface.co/bunnycore/HyperLlama-3.1-8B)

## 🧩 Configuration

```yaml

slices:
  - sources:
    - model: cognitivecomputations/Dolphin-2.9.1-Phi-3-Kensho-4.5B-abliterated-v3
      layer_range: [15, 29]
  - sources:
    - model: bunnycore/HyperLlama-3.1-8B
      layer_range: [20, 32]
merge_method: passthrough
dtype: bfloat16


```