---
license: apache-2.0
pipeline_tag: text-generation
tags:
- safetensors
- llama
- not-for-all-audiences
- nsfw
- rp
- roleplay
language:
- en
---

# ⚡ExLlamaV2 quant of : [InfinityRP-v2-8B](https://huggingface.co/Endevor/InfinityRP-v2-8B)
> [!note]
> ➡️ **Exl2 version :** [0.0.20](https://github.com/turboderp/exllamav2/releases/tag/v0.0.20)<br/>
> ➡️ **Cal. dataset :** Default.
<figure>
  <img width="20%" src="https://cdn-uploads.huggingface.co/production/uploads/6512562f8c0f10eedb1c64d7/O_-ZN2wA0JrG6RcXkp6hn.gif"></img>
  <figcaption>Forgot to save the measurement file...</figcaption>
</figure>


![example](https://files.catbox.moe/joazop.png)

The idea is the same as [InfinityRP v1](https://huggingface.co/Endevor/InfinityRP-v1-7B), but this one is Llama 3 with 16k ctx! Have fun...

### Prompt format: Alpaca.
``"You are now in roleplay chat mode. Engage in an endless chat, always with a creative response. Follow lengths very precisely and create paragraphs accurately. Always wait your turn, next actions and responses. Your internal thoughts are wrapped with ` marks."``

**User Message Prefix = ### Input:**

**Assistant Message Prefix = ### Response:**

**System Message Prefix = ### Instruction:**

**Turn on "Include Names"** (optional)

### Text Length: (use on your System Prompt or ### Response:)
Response: (length = medium) <- [tiny, micro, short, medium, long, enormous, huge, massive, humongous]

### Example:

![example](https://files.catbox.moe/t3hcez.png)