Cursor 联创 Aman Sanger 表示，团队在基于 perplexity 的评测中对比多个基座模型后选定 Kimi k2.5 作为 Composer-2 的基座，随后进行继续预训练和高算力 RL（4 倍规模扩展），结合 Fireworks 的推理与 RL sampler 使 Composer-2 达到前沿水平。他承认博客最初未提及 Kimi 基座是失误，下次会修正；此前 Kimi 官方已祝贺 Cursor 发布 Composer 2，并说明其通过 Fireworks 托管的 RL 与推理平台以授权商业合作方式接入。
Cursor 联创亲述 Composer-2 的模型来源与训练路径，读者可据此了解强基座加 CPT 和 RL 如何组合成前沿编码模型。
We've evaluated a lot of base models on perplexity-based evals and Kimi k2.5 proved to be the strongest!
After that, we do continued pre-training and high-compute RL (a 4x scale-up).
The combination of the strong base, CPT and RL, and Fireworks' inference and RL samplers make Composer-2 frontier level.
It was a miss to not mention the Kimi base in our blog from the start. We'll fix that for the next model.
Congrats to the @cursor_ai team on the launch of Composer 2! We are proud to see Kimi-k2.5 provide the foundation. Seeing our model integrated effectively through Cursor's continued pretraining & high-compute RL training is the open model ecosystem we love to support. Note: Cursor accesses Kimi-k2.5 via @FireworksAI_HQ ' hosted RL and inference platform as part of an authorized commercial partnership.在 X 查看被引用的帖子
来源：Aman Sanger · x.com