ReadyArt's Broken-Tutu-24B-Unslop-v2.0 is a 24 billion parameter language model based on mistralai/Mistral-Small-24B-Instruct-2501, fine-tuned for extreme roleplay and unaligned content generation. It features an expanded 43 million token dataset with zero 'slop' and enhanced unalignment for character integrity. This model excels at coherent, long-form multi-character scenarios with superior instruction following, while maintaining anti-impersonation guards.
No reviews yet. Be the first to review!
Hugging Face