Kev 系列开源小模型发布：兼容 Jev 的 System One 接口
Jared Palmer 放出 Kev-0.6B/4B/8B，用 Qwen3 加 LoRA 与指针头复刻 Jev 式决策模型，改个 base_url 就能接入 TypeSafe SDK，8B 在域外数据上达 79.6%。
UPDATE: Kev-0.6B, 4B, and 8B are now available. Kev is a family of small open source Jev-like decision models you can train and run yourself. This new family is based on Qwen3 using the same LoRA + small pointer head technique as before, but scaled up. Out of domain, on data Kev never trained on: Kev-8B 79.6%, Jev 85.7%. • Drop-in TypeSafe System One API; their SDK works with one `base_url` change • Kev-4B serves on a 32 GB Mac in bf16: ~300 ms for five questions, ~40 ms on an H100 • Repeated documents hit a KV cache: 2-2.5x faster • Apache 2.0 License. Kev-4B trains in 40 minutes on one H100. Kev-8B in 83 minutes. Code, weights, evals: https://github.com/jaredpalmer/kev
这条是引用着另一条写的：「Kev-0.5B：可在 MacBook 上跑的开源 Jev 式决策模型」