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.
[#]- Move # lines up, cursor after indent
，推荐阅读WhatsApp Web 網頁版登入获取更多信息
ФБР предупредило Калифорнию о возможной атаке Ирана20:49。谷歌对此有专业解读
Лига чемпионов|1/8 финала. 1-й матч。wps对此有专业解读
站在人均预期寿命79.25岁的新台阶上，往回看，“十四五”时期，我国人均预期寿命提升了1岁多；往前看，未来的提升空间在哪里？我的思考是：不只是单纯延长绝对的寿命，而要注重提升健康的寿命。健康中国绝不是简单的人均寿命数字提升，而是让全体人民都能实现活得长、活得健康，而且活得有质量。