AI 摘要
如何训练出在终端和编码方面能力强大的小型智能体模型?现宣布推出 OpenThoughts-Agent 和 OpenThinkerAgent-32B,这是基于 Qwen-3 的最强开放数据智能体模型,在 7 项智能体基准测试中平均得分 44.8%。Nathan Lambert 表示这是急需的数据发布,很兴奋。
A much needed data release! Excited to tinker with the data.
How can we train small agentic models that are highly capable of terminal use and coding? Announcing OpenThoughts-Agent + OpenThinkerAgent-32B, the strongest Qw...