---
license: apache-2.0
tags:
- safetensors
- llama
- rp
- roleplay
- sillytavern
language:
- en
---
> [!TIP]
> My upload speeds have been cooked and unstable lately.
> Realistically I'd need to move to get a better provider.
> If you **want** and you are able to, you can [**support that endeavor and others here (Ko-fi)**](https://ko-fi.com/Lewdiculous). I apologize for disrupting your experience.
# #llama-3 #roleplay
GGUF-IQ-Imatrix quants for [Endevor/InfinityRP-v2-8B](https://huggingface.co/Endevor/InfinityRP-v2-8B).
Back at it!
Lewdiculous: "Personally I still prefer the first version based on Mistral, this one hates asterisks."
> [!IMPORTANT]
> These quants have been done after the fixes from [llama.cpp/pull/6920](https://github.com/ggerganov/llama.cpp/pull/6920).
> Use **KoboldCpp version 1.64** or higher.
> [!NOTE]
> **Prompt formatting...**
> Alpaca prompt format recommended.
> A safe starting SillyTavern preset can be found [here (simple)](https://huggingface.co/Lewdiculous/Model-Requests/tree/main/data/presets/lewdicu-3.0.2-mistral-0.2).
# Original model information by the author:
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:
