A small open model that rewrites AI-styled English prose into more natural human writing. It is a full fine-tune of Qwen3-4B (all four billion weights updated) on 2,629 pairs of (AI-styled passage, human original). The human side is public domain: 2,000 passages from books on Project Gutenberg and 629 passages of modern prose from US federal agencies whose public-domain basis was checked page by page. The AI-styled side was written by OpenAI gpt-4o-mini and DeepSeek-chat. The Open Humanizer is a public research and educational model created to demonstrate the general approach used to develop AI text humanization systems. It is separate from the production models used by GoHumanize.ai, but it reflects many of the same high-level principles: careful dataset preparation, transformation of source text into training pairs, model fine-tuning, evaluation and iterative improvement. It is not intended to reproduce the architecture, data, configuration or performance of the production systems, and it makes no claim about AI detectors. Everything about the project (dataset, code, evaluation, write-up): https://gohumanize.ai/open-model A humanizer can fail by handing its input back almost…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: gohumanize
Теги: gguf, qwen3, humanizer, text-rewriting, style-transfer, unsloth, full-fine-tune, conversational
Лайков: 3 | Загрузок: 2,195
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.