---
license: llama3
tags:
- moe
language:
- en
---
**Exllamav2** quant (**exl2** / **2.5 bpw**) made with ExLlamaV2 v0.0.21

Other EXL2 quants:
| **Quant** | **Model Size** | **lm_head** |
| ----- | ---------- | ------- |
|<center>**[2.2](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-2_2bpw_exl2)**</center> | <center>7777 MB</center> | <center>6</center> |
|<center>**[2.5](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-2_5bpw_exl2)**</center> | <center>8519 MB</center> | <center>6</center> |
|<center>**[3.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-3_0bpw_exl2)**</center> | <center>9944 MB</center> | <center>6</center> |
|<center>**[3.5](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-3_5bpw_exl2)**</center> | <center>11365 MB</center> | <center>6</center> |
|<center>**[3.75](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-3_75bpw_exl2)**</center> | <center>12080 MB</center> | <center>6</center> |
|<center>**[4.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-4_0bpw_exl2)**</center> | <center>12789 MB</center> | <center>6</center> |
|<center>**[4.25](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-4_25bpw_exl2)**</center> | <center>13503 MB</center> | <center>6</center> |
|<center>**[5.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-5_0bpw_exl2)**</center> | <center>15632 MB</center> | <center>6</center> |
|<center>**[6.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-6_0bpw_exl2)**</center> | <center>18594 MB</center> | <center>8</center> |
|<center>**[6.5](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-6_5bpw_exl2)**</center> | <center>19969 MB</center> | <center>8</center> |
|<center>**[8.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-8_0bpw_exl2)**</center> | <center>24115 MB</center> | <center>8</center> |


<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/OuMe79ZQPdCX01rTdfgXn.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/OuMe79ZQPdCX01rTdfgXn.png" style="width: 96%; margin: auto;" >
</div>

(Maybe i'll change the waifu picture later)

> [!NOTE]
> [GGUF/Exl2 quants](https://huggingface.co/collections/xxx777xxxASD/snowstorm-4x8b-664b52a1d2a12e515efb5680)


Experimental RP-oriented MoE, the idea was to get a model that would be equal to or better than Mixtral 8x7B and it's finetunes in RP/ERP tasks.

### Llama 3 SnowStorm 4x8B
```
base_model: NeverSleep_Llama-3-Lumimaid-8B-v0.1-OAS
gate_mode: random
dtype: bfloat16
experts_per_token: 2
experts:
  - source_model: ChaoticNeutrals_Poppy_Porpoise-v0.7-L3-8B
  - source_model: NeverSleep_Llama-3-Lumimaid-8B-v0.1-OAS
  - source_model: openlynn_Llama-3-Soliloquy-8B-v2
  - source_model: Sao10K_L3-8B-Stheno-v3.1
```


## Models used

- [ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B)
- [NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS)
- [openlynn/Llama-3-Soliloquy-8B-v2](https://huggingface.co/openlynn/Llama-3-Soliloquy-8B-v2)
- [Sao10K/L3-8B-Stheno-v3.1](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.1)


## Difference(from ChaoticSoliloquy v1.5)

- Update from [NeverSleep/Llama-3-Lumimaid-8B-v0.1](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1) to [NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS)
- Update from [openlynn/Llama-3-Soliloquy-8B-v1](https://huggingface.co/openlynn/Llama-3-Soliloquy-8B-v1) to [openlynn/Llama-3-Soliloquy-8B-v2](https://huggingface.co/openlynn/Llama-3-Soliloquy-8B-v2)
- Update from [Sao10K/L3-Solana-8B-v1](https://huggingface.co/Sao10K/L3-Solana-8B-v1) to [Sao10K/L3-8B-Stheno-v3.1](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.1)


## Vision

[llama3_mmproj](https://huggingface.co/ChaoticNeutrals/LLaVA-Llama-3-8B-mmproj-Updated)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f5e51289c121cb864ba464/yv4C6NalqORLjvY3KKZk8.png)


## Prompt format: Llama 3