Downloads · 30 days
689
4% of all-time downloads
Lewdiculous/Poppy_Porpoise-1.0-L3-8B-GGUF-IQ-Imatrix
Poppy_Porpoise-1.0-L3-8B-GGUF-IQ-Imatrix is a machine learning model from Lewdiculous. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.
[!CAUTION] broken Use version 0.72 instead. This model is now deprecated since the author has identified significant issues with it, this is considered broken and is only still kept here for archiving.
Downloads · 30 days
689
4% of all-time downloads
All-time downloads
16.5K
Public
Repo size
56 GB
Likes
15
Public
Click a slice to open those files.
.gguf56 GB · 100%
From the Hugging Face model README
[!CAUTION]
#broken
This model is now deprecated since the author has identified significant issues with it, this is considered #broken and is only still kept here for archiving.
My GGUF-IQ-Imatrix quants for Nitral-AI/Poppy_Porpoise-1.0-L3-8B.
"Isn't Poppy the cutest Porpoise?"
[!IMPORTANT] Quantization process: <br> For future reference, these quants have been done after the fixes from #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.
<!-- > Check [**discussions such as this one**](https://huggingface.co/Virt-io/SillyTavern-Presets/discussions/5#664d6fb87c563d4d95151baa) for other recommendations and samplers. -->[!NOTE] General usage: <br> Use the latest version of KoboldCpp. <br> Remember that you can also use
--flashattentionon 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 and here, respectively.
Presets: <br> Some compatible SillyTavern presets can be found here (New Poppy-1.0 Presets) or here (Virt's Roleplay Presets). <br>
[!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). <br>
Author-support: <br> You can support the author at their own page.

"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.

Detailed results can be found here
| 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 |