|
--- |
|
license: cc-by-nc-4.0 |
|
language: |
|
- en |
|
inference: false |
|
tags: |
|
- roleplay |
|
- llama3 |
|
- sillytavern |
|
--- |
|
|
|
# #roleplay #sillytavern #llama3 |
|
|
|
My GGUF-IQ-Imatrix quants for [**Nitral-AI/Poppy_Porpoise-1.0-L3-8B**](https://huggingface.co/Nitral-AI/Poppy_Porpoise-1.0-L3-8B). |
|
|
|
"Isn't Poppy the cutest [Porpoise](https://g.co/kgs/5C2zP3r)?" |
|
|
|
> [!IMPORTANT] |
|
> **Quantization process:** <br> |
|
> For future reference, these quants have been done after the fixes from [**#6920**](https://github.com/ggerganov/llama.cpp/pull/6920) have been merged. <br> |
|
> Since the original model was already an FP16, imatrix data was generated from the FP16-GGUF and the conversions as well. <br> <!-- This was a bit more disk and compute intensive but hopefully avoided any losses during conversion. <br> --> |
|
> If you noticed any issues let me know in the discussions. |
|
|
|
> [!NOTE] |
|
> **General usage:** <br> |
|
> Use the latest version of **KoboldCpp**. <br> |
|
> Remember that you can also use `--flashattention` on KoboldCpp now even with non-RTX cards for reduced VRAM usage. <br> |
|
> For **8GB VRAM** GPUs, I recommend the **Q4_K_M-imat** quant for up to 12288 context sizes. <br> |
|
> For **12GB VRAM** GPUs, the **Q5_K_M-imat** quant will give you a great size/quality balance. <br> |
|
> |
|
> **Resources:** <br> |
|
> You can find out more about how each quant stacks up against each other and their types [**here**](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) and [**here**](https://rentry.org/llama-cpp-quants-or-fine-ill-do-it-myself-then-pt-2), respectively. |
|
> |
|
> **Presets:** <br> |
|
> Some compatible SillyTavern presets can be found [**here (New Poppy-1.0 Presets)**](https://huggingface.co/Nitral-AI/Poppy_Porpoise-1.0-L3-8B/tree/main/Porpoise_1.0-Presets) or [**here (Virt's Roleplay Presets)**](https://huggingface.co/Virt-io/SillyTavern-Presets). <br> |
|
<!-- > Check [**discussions such as this one**](https://huggingface.co/Virt-io/SillyTavern-Presets/discussions/5#664d6fb87c563d4d95151baa) for other recommendations and samplers. |
|
--> |
|
|
|
> [!TIP] |
|
> **Personal-support:** <br> |
|
> I apologize for disrupting your experience. <br> |
|
> Currently I'm working on moving for a better internet provider. <br> |
|
> If you **want** and you are **able to**... <br> |
|
> You can [**spare some change over here (Ko-fi)**](https://ko-fi.com/Lewdiculous). <br> |
|
> |
|
> **Author-support:** <br> |
|
> You can support the author [**at their own page**](https://huggingface.co/Nitral-AI). |
|
|
|
 |
|
|
|
## **Original model text information:** |
|
|
|
**"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.** |
|
|
|
# Presets in repo folder: |
|
|
|
* https://huggingface.co/Nitral-AI/Poppy_Porpoise-1.0-L3-8B/tree/main/Porpoise_1.0-Presets |
|
|
|
# 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 here: [Llava-MMProj file](https://huggingface.co/Nitral-AI/Llama-3-Update-2.0-mmproj-model-f16). |
|
|
|
* You can load the **mmproj** file by using the corresponding section in the interface: |
|
|
|
 |
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) |
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Nitral-AI__Poppy_Porpoise-0.85-L3-8B) |
|
|
|
| Metric |Value| |
|
|---------------------------------|----:| |
|
|Avg. |69.24| |
|
|AI2 Reasoning Challenge (25-Shot)|63.40| |
|
|HellaSwag (10-Shot) |82.89| |
|
|MMLU (5-Shot) |68.04| |
|
|TruthfulQA (0-shot) |54.12| |
|
|Winogrande (5-shot) |77.90| |
|
|GSM8k (5-shot) |69.07| |
|
|
|
|
