Nous Research has released Arete-27B, a supervised fine-tune of Alibaba’s Qwen3.8-27B. Arete-27B is a 27B open-weight model that strips Chinese state framing from Qwen’s answers. On Nous’s own 803-prompt eval, answers containing propaganda fell from 22% to 0.9%. Developers get Qwen-class agentic skill without state-aligned answers. The weights, eval and training data are all public.
Arete-27B is Qwen3.8-27B after supervised fine-tuning only. Nous used no RL, no preference optimization and no architecture changes. The license is Apache 2.0, matching the base model.
Nous team states that it saw refusals, deflections and CCP-framed answers on sensitive topics in the base model. It picked Qwen3.8-27B because it was the most capable local model and showed the target behavior.
The teacher was Inkling, an open model from Thinking Machines. Nous chose an open teacher to avoid terms-of-use limits on distillation. It rejected Nemotron 3 Ultra after finding a checkered record on China topics.
Source: MarkTechPost — Read the full article on the original site ↗