产品62
vLLM 支持上海 AI 实验室 Sage S2.1 Flash 多模态模型
原标题:Great work from @sageai_official on Sage S2.1 Flash, now supported in vLLM!
vLLM 宣布已支持 Sage S2.1 Flash,该模型由 @sageai_official 推出,面向需要多轮分析与验证的科研任务。模型把科学数据理解与检索、编码、工具调用结合起来,可依据中间结果和视觉反馈调整后续步骤,覆盖分子图、晶体结构、蛋白质序列等 10 余类科学输入。权重已在 Hugging Face 和 ModelScope 发布,SGLang 也已支持。
中文译文尚未完成,先为你展示原文。
Great work from @sageai_official on Sage S2.1 Flash, now supported in vLLM!
From molecular graphs to protein structures, it brings scientific data understanding together with retrieval, coding and tool use—checking intermediate results and refining the next step.
Weights are available on @HuggingFace and @ModelScope2022.
🚀 Introducing Sage S2.1 Flash, our new multimodal model designed for research tasks requiring multiple rounds of analysis and verification. 1⃣Combines scientific data understanding with information retrieval, coding, and tool use. 2⃣Uses specialized software to perform analyses, verify results against intermediate outputs and visual feedback, and adjust subsequent steps accordingly. 3⃣Built on the unified representation architecture of Sage SciPerception, supporting more than 10 types of scientific input, including molecular graphs, crystal structures, protein sequences, and 3D protein structures. 4⃣Ranks first on MLE-bench Lite (90.3), OfficeQA Pro (72.2), Harvey LAB (25.0), and SpreadsheetBench 2 (37.1). 🥰Now supported by vLLM (@vllm_project) and SGLang ( @lmsysorg ) — with more ecosystem integrations on the way. 🤗 Model: @HuggingFace https://huggingface.co/internlm/Sage-S2.1-Flash @ModelScope2022 https://www.modelscope.cn/models/Shanghai_AI_Laboratory/Sage-S2.1-Flash 🤗 Try it now: https://discovery.intern-ai.org.cn/token-plan/home查看原帖
