---
license: cc-by-nc-4.0
tags:
- roleplay
- llama3
- sillytavern
---

**[Uploading...]**

> [!TIP]
> **Support:** <br>
> My upload speeds have been cooked and unstable lately. <br>
> Realistically I'd need to move to get a better provider. <br>
> If you **want** and you are able to... <br>
> You can [**support my various endeavors here (Ko-fi)**](https://ko-fi.com/Lewdiculous). <br>
> I apologize for disrupting your experience.

GGUF-IQ-Imatrix quants for [NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS).

"This model have received the Orthogonal Activation Steering treatment, **meaning it will rarely refuse any request.**"

> [!IMPORTANT]  
> **Relevant:** <br>
> These quants have been done after the fixes from [**llama.cpp/pull/6920**](https://github.com/ggerganov/llama.cpp/pull/6920) have been merged. <br>
> Use **KoboldCpp** version **1.64** or higher, make sure you're up-to-date.

> [!WARNING]
> Compatible SillyTavern presets [here (simple)](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B/tree/main/Official%20Poppy%20Porpoise%20ST%20Presets)) or [here (Virt's Roleplay Presets - recommended)](https://huggingface.co/Virt-io/SillyTavern-Presets). <br>
> Use the latest version of KoboldCpp. **Use the provided presets for testing.** <br>
> Feedback and support for the Authors is always welcome. <br>
> If there are any issues or questions let me know.

> [!NOTE]
> For **8GB VRAM** GPUs, I recommend the **Q4_K_M-imat** quant for up to 12288 context sizes.

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/JUxfdTot7v7LTdIGYyzYM.png)

**Original model information:**

## Lumimaid 0.1

<center><div style="width: 100%;">
    <img src="https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/d3QMaxy3peFTpSlWdWF-k.png" style="display: block; margin: auto;">
</div></center>

This model uses the Llama3 **prompting format**

Llama3 trained on our RP datasets, we tried to have a balance between the ERP and the RP, not too horny, but just enough.

We also added some non-RP dataset, making the model less dumb overall. It should look like a 40%/60% ratio for Non-RP/RP+ERP data.

This model includes the new Luminae dataset from Ikari.

This model have received the Orthogonal Activation Steering treatment, meaning it will rarely refuse any request.

If you consider trying this model please give us some feedback either on the Community tab on hf or on our [Discord Server](https://discord.gg/MtCVRWTZXY).

## Credits:
- Undi
- IkariDev

## Description

This repo contains FP16 files of Lumimaid-8B-v0.1-OAS.

Switch: [8B](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1) - [70B](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-70B-v0.1) - [70B-alt](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-70B-v0.1-alt) - [8B-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS) - [70B-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-70B-v0.1-OAS)

## Training data used:
- [Aesir datasets](https://huggingface.co/MinervaAI)
- [NoRobots](https://huggingface.co/datasets/Doctor-Shotgun/no-robots-sharegpt)
- [limarp](https://huggingface.co/datasets/lemonilia/LimaRP) - 8k ctx
- [toxic-dpo-v0.1-sharegpt](https://huggingface.co/datasets/Undi95/toxic-dpo-v0.1-sharegpt)
- [ToxicQAFinal](https://huggingface.co/datasets/NobodyExistsOnTheInternet/ToxicQAFinal)
- Luminae-i1 (70B/70B-alt) (i2 was not existing when the 70b started training) | Luminae-i2 (8B) (this one gave better results on the 8b) - Ikari's Dataset
- [Squish42/bluemoon-fandom-1-1-rp-cleaned](https://huggingface.co/datasets/Squish42/bluemoon-fandom-1-1-rp-cleaned) - 50% (randomly)
- [NobodyExistsOnTheInternet/PIPPAsharegptv2test](https://huggingface.co/datasets/NobodyExistsOnTheInternet/PIPPAsharegptv2test) - 5% (randomly)
- [cgato/SlimOrcaDedupCleaned](https://huggingface.co/datasets/cgato/SlimOrcaDedupCleaned) - 5% (randomly)
- Airoboros (reduced)
- [Capybara](https://huggingface.co/datasets/Undi95/Capybara-ShareGPT/) (reduced)


## Models used (only for 8B)

- Initial LumiMaid 8B Finetune
- Undi95/Llama-3-Unholy-8B-e4
- Undi95/Llama-3-LewdPlay-8B

## Prompt template: Llama3

```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>
```

## Others

Undi: If you want to support us, you can [here](https://ko-fi.com/undiai).

IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek