---
language:
- en
license: llama3
tags:
- moe
---

<style>
.image-container {
  position: relative;
  display: inline-block;
}

.image-container img {
  display: block;
  border-radius: 10px;
  box-shadow: 0 0 1px rgba(0, 0, 0, 0.3);
}

.image-container::before {
  content: "";
  position: absolute;
  top: 0px;
  left: 20px;
  width: calc(100% - 40px);
  height: calc(100%);
  background-image: url("https://cdn-uploads.huggingface.co/production/uploads/64f5e51289c121cb864ba464/O0FlWv4L8ZnehOGETw7qt.png");
  background-size: cover;
  filter: blur(10px);
  z-index: -1;
}
</style>
<br>

<div class="image-container">
  <img src="https://cdn-uploads.huggingface.co/production/uploads/64f5e51289c121cb864ba464/O0FlWv4L8ZnehOGETw7qt.png" style="width: 96%; margin: auto;" >
</div>

Experimental RP-oriented MoE

### Llama 3 ClaudeMaid v1.0 4x8B
```
base_model: NeverSleep_Lumimaid-v0.2-8B
gate_mode: random
dtype: bfloat16
experts_per_token: 2
experts:
  - source_model: aifeifei798_DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored
  - source_model: Nitral-AI_Sekhmet_Bet-L3.1-8B-v0.2
  - source_model: NeverSleep_Lumimaid-v0.2-8B
  - source_model: Undi95_Meta-Llama-3.1-8B-Claude-bf16
```

## Usage

It seems like 1.71 koboldcpp can't run MoE llama-3.1 models yet, or perhaps im just dumb and messed something up

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f5e51289c121cb864ba464/sTM3GUVMucM_AnIk8iG7H.png)

If anyone has simmilar problem - run the model directly from llama.cpp, here's simple open source GUI(Windows) you can use if the console is your worst enemy

Link

## Models used

- [NeverSleep/Lumimaid-v0.2-8B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-8B)
- [Undi95/Meta-Llama-3.1-8B-Claude](https://huggingface.co/Undi95/Meta-Llama-3.1-8B-Claude)
- [Nitral-AI/Sekhmet_Bet-L3.1-8B-v0.2](https://huggingface.co/Nitral-AI/Sekhmet_Bet-L3.1-8B-v0.2)
- [aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored](https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored)


## Prompt format: Llama 3