authormist/authormist-originality

AuthorMist Originality is a 3.1 billion parameter language model based on Qwen2.5-3B Instruct, developed by AuthorMist. It is specifically fine-tuned using reinforcement learning to transform AI-generated text into more human-like writing while preserving meaning, primarily to evade AI text detection systems. This model excels at reducing detectability across multiple AI text detection systems, maintaining high semantic similarity with original text. It is optimized for texts ranging from 100 to 500 words across various domains.