|
--- |
|
base_model: |
|
- Nitral-AI/PP_0.71b |
|
- Nitral-AI/PP_0.71a |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
license: other |
|
--- |
|
|
|
6.5bpw exl2 quant of : https://huggingface.co/Nitral-AI/Poppy_Porpoise-0.72-L3-8B |
|
|
|
Should be perfect for 12k context for 8GB VRAM Cards (if using linux) |
|
|
|
# "Poppy Porpoise" is a cutting-edge AI roleplay assistant based on the Llama 3 8B model, specializing in crafting unforgettable narrative experiences. With its advanced language capabilities, Poppy expertly immerses users in an interactive and engaging adventure, tailoring each adventure to their individual preferences. |
|
|
|
 |
|
|
|
# Quants Available From Lewdiculus: https://huggingface.co/Lewdiculous/Poppy_Porpoise-0.72-L3-8B-GGUF-IQ-Imatrix |
|
|
|
# Recomended ST Presets:(Updated for 0.72) [Porpoise Presets](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B/tree/main/Official%20Poppy%20Porpoise%20ST%20Presets) |
|
|
|
If you want to use vision functionality: |
|
|
|
* You must use the latest versions of [Koboldcpp](https://github.com/LostRuins/koboldcpp). |
|
|
|
# To use the multimodal capabilities of this model and use **vision** you need to load the specified **mmproj** file, this can be found inside this model repo. [Llava MMProj](https://huggingface.co/ChaoticNeutrals/LLaVA-Llama-3-8B-mmproj) |
|
|
|
* You can load the **mmproj** by using the corresponding section in the interface: |
|
|
|
 |
