A growing countertrend towards smaller (opens in new tab) models aims to boost efficiency, enabled by careful model design and data curation – a goal pioneered by the Phi family of models (opens in new tab) and furthered by Phi-4-reasoning-vision-15B. We specifically build on learnings from the Phi-4 and Phi-4-Reasoning language models and show how a multimodal model can be trained to cover a wide range of vision and language tasks without relying on extremely large training datasets, architectures, or excessive inference‑time token generation. Our model is intended to be lightweight enough to run on modest hardware while remaining capable of structured reasoning when it is beneficial. Our model was trained with far less compute than many recent open-weight VLMs of similar size. We used just 200 billion tokens of multimodal data leveraging Phi-4-reasoning (trained with 16 billion tokens) based on a core model Phi-4 (400 billion unique tokens), compared to more than 1 trillion tokens used for training multimodal models like Qwen 2.5 VL (opens in new tab) and 3 VL (opens in new tab), Kimi-VL (opens in new tab), and Gemma3 (opens in new tab). We can therefore present a compelling option compared to existing models pushing the pareto-frontier of the tradeoff between accuracy and compute costs.
Which means, yes, I wrote a looping factorial program out of candy.。新收录的资料是该领域的重要参考
，推荐阅读新收录的资料获取更多信息
一方面，欧美发达国家电网进入集中更新周期，大量运行40—50年的老旧设施亟待替换；另一方面，新兴市场电力基础设施仍处建设阶段，新增装机与电网扩容同步推进。与此同时，新能源大规模并网与数据中心用电激增，对高效率、高可靠性的电力设备提出更高标准。供需错位之下，行业景气度迅速抬升。。业内人士推荐新收录的资料作为进阶阅读
Knowledge Retrieval（规范/PRD/接口文档）
В России начнут строже наказывать за нарушение правил пересечения границы20:12