README.md

---
license: apache-2.0
tags:
- moe
- merge
- mergekit
- lazymergekit
- cognitivecomputations/dolphin-2_6-phi-2
- lxuechen/phi-2-dpo
- Yhyu13/phi-2-sft-dpo-gpt4_en-ep1
- mrm8488/phi-2-coder
---

![](https://i.imgur.com/UOb2fvh.jpg)

# phixtral-4x2.8

phixtral-2x2.8 is a Mixure of Experts (MoE) made with the following models using a custom version of mergekit:
* [cognitivecomputations/dolphin-2_6-phi-2](https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2)
* [lxuechen/phi-2-dpo](https://huggingface.co/lxuechen/phi-2-dpo)
* [Yhyu13/phi-2-sft-dpo-gpt4_en-ep1](https://huggingface.co/Yhyu13/phi-2-sft-dpo-gpt4_en-ep1)
* [mrm8488/phi-2-coder](https://huggingface.co/mrm8488/phi-2-coder)

## 🧩 Configuration

```yaml
base_model: cognitivecomputations/dolphin-2_6-phi-2
gate_mode: cheap_embed
experts:
  - source_model: cognitivecomputations/dolphin-2_6-phi-2
    positive_prompts: [""]
  - source_model: lxuechen/phi-2-dpo
    positive_prompts: [""]
  - source_model: Yhyu13/phi-2-sft-dpo-gpt4_en-ep1
    positive_prompts: [""]
  - source_model: mrm8488/phi-2-coder
    positive_prompts: [""]
```

## 💻 Usage

This architecture is not compatible with the transformers library. I'm working on hacking something to run it. Contact me if you're interested!