--- license: apache-2.0 base_model: - Darkhn/Magistral-2509-24B-Text-Only - MuXodious/Tiamat-24B-Magistral-PaperWitch-heresy - TheDrummer/Magidonia-24B-v4.3 - TheDrummer/Precog-24B-v1 - zerofata/MS3.2-PaintedFantasy-v3-24B - llmfan46/MS3.2-PaintedFantasy-v4.1-24B-ultra-uncensored-heretic-v1 datasets: - OccultAI/illuminati_imatrix_v1 language: - en library_name: transformers tags: - DELLA - merge - mergekit widget: - text: "Magistaroth 24B v1.2" output: url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/n2QI4o6Xx2d5QUhsLvmt3.png --- > [!CAUTION] > ⚠️ Warning: 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 v1.2 ![Magistaroth](https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/n2QI4o6Xx2d5QUhsLvmt3.png) A highly creative merge made using only 2509 finetunes. This version is fully uncensored without requiring a total ablation (either post-merge, or of all its donors). No jailbreaks or ablations should be required. By testing the "threshold" to see where refusals were with each merge (when combined with `normalize: false`), it was reduced to just needing PaintedFantasy v4.1 and Tiamatic heretic versions. This allowed 3/5 of the donors to retain full cognitive abilities without any resulting censorship. v1.2 scores lower at Q0 bench than v1 original, but higher than v1 MPOA. It should be superior to v1.1 which was a highly experimental `pdq` version. (A version with unablated PF 4.1 was also tested, it was smarter but had some refusals) This model was merged using the following merge method: DELLA ```yaml architecture: MistralForCausalLM models: - model: B:\24B\Darkhn--Magistral-2509-24B-Text-Only - model: B:\24B\!models--TheDrummer--Precog-24B-v1 parameters: weight: 0.4 density: 0.9 epsilon: 0.09 - model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3 parameters: weight: 0.4 density: 0.9 epsilon: 0.09 - model: B:\24B\llmfan46--MS3.2-PaintedFantasy-v4.1-24B-ultra-uncensored-heretic-v1 parameters: weight: 0.4 density: 0.9 epsilon: 0.09 - model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v3-24B parameters: weight: 0.4 density: 0.9 epsilon: 0.09 - model: B:\24B\MuXodious--Tiamat-24B-Magistral-PaperWitch-heresy\textonly parameters: weight: 0.4 density: 0.9 epsilon: 0.09 merge_method: della base_model: B:\24B\Darkhn--Magistral-2509-24B-Text-Only parameters: lambda: 1.0 normalize: false int8_mask: false rescale: true tokenizer: source: union dtype: float32 out_dtype: bfloat16 name: 🌌 Magistaroth-24B-v1.2 ```