README.md

---
license: llama3
language:
- en
tags:
- moe
---
![image/png](/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F64f5e51289c121cb864ba464%2FjgyhmI451GRXri5hEj3lh.png%3C%2Fspan%3E)%3C!-- HTML_TAG_END -->
(Maybe i'll change the waifu picture later)

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

[GGUF, Exl2](https://huggingface.co/collections/xxx777xxxASD/chaoticsoliloquy-4x8b-6628a759b5a60d8d3f51ed62)

### ChaoticSoliloquy-4x8B
```
base_model: jeiku_Chaos_RP_l3_8B
gate_mode: random
dtype: bfloat16
experts_per_token: 2
experts:
  - source_model: ChaoticNeutrals_Poppy_Porpoise-v0.6-L3-8B
  - source_model: jeiku_Chaos_RP_l3_8B
  - source_model: openlynn_Llama-3-Soliloquy-8B
  - source_model: Sao10K_L3-Solana-8B-v1
```

## Models used

- [ChaoticNeutrals/Poppy_Porpoise-v0.6-L3-8B](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.6-L3-8B)
- [jeiku/Chaos_RP_l3_8B](https://huggingface.co/jeiku/Chaos_RP_l3_8B)
- [openlynn/Llama-3-Soliloquy-8B](https://huggingface.co/openlynn/Llama-3-Soliloquy-8B)
- [Sao10K/L3-Solana-8B-v1](https://huggingface.co/Sao10K/L3-Solana-8B-v1)

## Vision

[llama3_mmproj](https://huggingface.co/ChaoticNeutrals/Llava_1.5_Llama3_mmproj)
![image/png](/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F64f5e51289c121cb864ba464%2Fyv4C6NalqORLjvY3KKZk8.png%3C%2Fspan%3E)%3C!-- HTML_TAG_END -->


## Prompt format: Llama 3