Nous Research发布基于Qwen3.8-27B的Arete-27B模型
Nous Research发布Arete-27B，基于阿里Qwen3.8-27B并用约5300万Token进行西方政治价值观微调。其自测称，模型宣传率由22%降至约1%，通用能力未明显下降。
Loading…
bibibi.ccbibibi.ccLoading…
Connect scattered updates into a story you can understand.
Nous Research发布Arete-27B，基于阿里Qwen3.8-27B并用约5300万Token进行西方政治价值观微调。其自测称，模型宣传率由22%降至约1%，通用能力未明显下降。
BlockBeats reported that Coinbase CEO Brian Armstrong said that, after fine-tuning Qwen3.5-9B with internal data, the company achieved better performance on fraud prevention tasks than some frontier models, with lower inference latency.Coinbase is simplifying the internal fine-tuning process.
