|
--- |
|
license: apache-2.0 |
|
tags: |
|
- safetensors |
|
- llama |
|
- rp |
|
- roleplay |
|
- sillytavern |
|
language: |
|
- en |
|
--- |
|
# #llama-3 #roleplay |
|
|
|
GGUF-IQ-Imatrix quants for [Endevor/InfinityRP-v2-8B](https://huggingface.co/Endevor/InfinityRP-v2-8B). <br> Back at it! |
|
|
|
> [!IMPORTANT] |
|
> These quants have been done after the fixes from [llama.cpp/pull/6920](https://github.com/ggerganov/llama.cpp/pull/6920). <br> |
|
> Use **KoboldCpp version 1.64** or higher. |
|
|
|
> [!NOTE] |
|
> **Prompt formatting...** <br> |
|
> Alpaca prompt format recommended. <br> |
|
> 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: |
|
|
|
 |
