47 lines
2.4 KiB
Markdown
47 lines
2.4 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
base_model:
|
||
|
|
- DarkArtsForge/Magistaroth-24B-v1
|
||
|
|
- mistralai/Magistral-Small-2509
|
||
|
|
- Gryphe/Tiamat-24B-Magistral
|
||
|
|
- TheDrummer/Magidonia-24B-v4.3
|
||
|
|
- TheDrummer/Precog-24B-v1
|
||
|
|
- zerofata/MS3.2-PaintedFantasy-v3-24B
|
||
|
|
- zerofata/MS3.2-PaintedFantasy-v4.1-24B
|
||
|
|
datasets:
|
||
|
|
- OccultAI/illuminati_imatrix_v1
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- pdq
|
||
|
|
- merge
|
||
|
|
- mergekit
|
||
|
|
widget:
|
||
|
|
- text: "Magistaroth 24B v1.1"
|
||
|
|
output:
|
||
|
|
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/n2QI4o6Xx2d5QUhsLvmt3.png
|
||
|
|
---
|
||
|
|
|
||
|
|
> [!CAUTION]
|
||
|
|
> <span style="color:red; font-weight:bold">⚠️ Warning:</span> This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use **Mistral Tekken** chat template.
|
||
|
|
>
|
||
|
|
|
||
|
|
# 🌌 Magistaroth 24B v1.1
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# Merge Method
|
||
|
|
A custom merge method known as `pdq` has been invented. Instead of using its own yaml, it acts as a post-merge processor which applies directly to the merged model using the [original yaml](https://huggingface.co/DarkArtsForge/Magistaroth-24B-v1/raw/main/mergekit_config.yml). `pdq` aims to enhance creativity by re-scanning the original donor models, encouraging them to explore the 'dark matter' regions of the vectors to synergistically augment the merged base with more unique novelty. For **Magistaroth v1.1**, I tested both the v1 `Della → PDQ → MPOA` and `Della → MPOA → PDQ`.
|
||
|
|
|
||
|
|
It turns out that both are very creative, and the `MPOA → PDQ` is interesting because it doesn't re-introduce any refusals, however, `PDQ → MPOA` is much smarter. The difference in Q0 bench reflects this (9451 vs 12648). `Scale 1.2` was the ablation threshold required to disable refusals. This has resulted in the most creative, detailed, and uncensored variant of the configurations tested.
|
||
|
|
|
||
|
|
### Bugs
|
||
|
|
A small risk of increased artifacts (missing spaces, word misspelled or repeated) might be noticed due to `pdq` pushing the limits of what's possible with transformers. These are rare and can be edited out if needed.
|
||
|
|
|
||
|
|
### Fully Uncensored
|
||
|
|
An unablated PDQ version was also tested (it has refusals) but it seems the ablated versions are more popular so I'm just releasing this one for now.
|
||
|
|
|
||
|
|
### Settings
|
||
|
|
- Recommended `temp 1.0` and `topnsigma 1.25`
|
||
|
|
- `Mistral Tekken` chat template
|