开源模型首次能看图听声，还公开了全部训练数据
开源大模型一直有个尴尬：权重开放，但训练数据、配方、评测标准往往藏着。Apertus 1.5 把「开放」做到了底——不只是模型，连数据准备、训练步骤、评测套件全部公开，而且只用公开数据、尊重网站爬虫的退出声明。技术上它把文本模型扩展成能看图听声的多模态推理器，上下文窗口拉到 26 万 token，数学推理靠一个「思考开关」就能提升 20 分。在同类全开源模型里，它的指令跟随能力甚至超过了所有对比的开权重模型。这不是你明天能装进产品的东西，但它证明了「不依赖少数几家公司的 AI 基础设施」在规模上可行——对关心 AI 权力集中、想看到替代方案的人来说，这是值得盯住的一条线。
📄 原文摘要(英文)
Language models are becoming infrastructure, and infrastructure built in the open, by public institutions, on documented data, is the alternative to dependence on a few providers; Apertus shows this is viable at scale. Apertus 1.5 extends the fully open Apertus family from text to multimodal reasoning. Continued pretraining of the Apertus 1.0 models, on 4T additional tokens for the 8B and 2T for the 70B, adds image and audio understanding and extends the context window fourfold to 262,144 tokens; multimodality enters through the tokenizer, the language-model head remains restricted to text, and the architecture is unchanged. Supervised finetuning, long-context finetuning, reinforcement learning with verifiable rewards, and preference alignment complete the released models. Thinking is a flag of the chat template rather than a separate model, and lifts mathematical reasoning by up to 20 points on the 8B model. The released models improve over their predecessors on nearly every benchmark; among fully open models of its class, the 8B leads on knowledge, instruction following, and cultural benchmarks, and its instruction following surpasses all compared models, including open-weight ones. On image and audio understanding, a first for the family, the models are competitive with fully open multimodal models, strongest on document understanding and long-form and lower-resource speech recognition, while specialized vision and audio models remain ahead on perception and transcription of English and other high-resource languages. As in Apertus 1.0, we train only on openly available data, respect crawler opt-outs retroactively, and exclude restrictively licensed material. We release the model weights, data preparation and training recipes, and evaluation suites under permissive licenses; openness extends to values, with the Apertus charter guiding alignment stages published alongside the models.