Clef 推出开放权重决策模型与新的 RL 微调平台
Clef: Open-weight decision models, and new RL fine-tuning platform
jasondavies 在 Hacker News 评论中表示，小参数模型已能完成这类任务、只是稍慢，他本地用 Qwen 0.8b 做基础图片分类耗时低于 500ms。该做法此前就已具备，作者从 Jev 引发的反响中判断市场兴趣足以支撑其作为独立产品提供。文中还提到有几个技术细节可显著降低延迟。
Smaller models have been able to do these sorts of tasks, but a little slower, for a while now. Give a small Qwen 3.8 model a classification task and force a structured output, and it'll do a good job. I've used Qwen 0.8b for basic image classification in <500ms on my local machine for a while now.
There are a few technical details that can reduce the latency significantly (covered in the post) but the real insight has been from watching the reaction to Jev and seeing that there's enough of a market interest to offer it as a distinct thing. The underlying concept/approach was already there.
来源：Hacker News · 首页 · news.ycombinator.com