公开预览版:仅展示平台目录与原作者卡片,不提供下载;院内智能体通过内网实例申请使用。

院内模型平台

经审核的医学与通用基础模型、公开医学数据集 · 院内网络可用

浏览全部模型 (197) → 浏览全部数据集 (93) →

模型 · 按科室

模型按该科室常用的数据类型归类(同一规则适用于所有模型),通用模型单独列出;数据集按数据的采集科室与解剖部位归类。

数据集 · 按科室

模型 · 按领域

按类别

下载量最高

🧩 openai/clip-vit-large-patch14
通用·自然图像通用 ·1.71 GB ·↓ 6,906,554 ·♥ 2132
Disclaimer: The model card is taken and modified from the official CLIP repository, it can be found here.
🧩 facebook/esm2_t33_650M_UR50D
分子/组学·分子/组学 ·2.61 GB ·↓ 4,762,004 ·♥ 104
ESM-2 is a state-of-the-art protein model trained on a masked language modelling objective. It is suitable for fine-tuning on a wide range o…
🧩 facebook/dinov2-base
通用·自然图像通用 ·0.35 GB ·↓ 3,098,453 ·♥ 214
Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper DINOv2: Learning Robust Visual Features witho…
🧩 facebook/dinov2-small
通用·自然图像通用 ·0.09 GB ·↓ 2,745,598 ·♥ 85
Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper DINOv2: Learning Robust Visual Features witho…
🧩 IDEA-Research/grounding-dino-base
通用·分割/检测/深度 ·0.93 GB ·↓ 2,149,367 ·♥ 224
The Grounding DINO model was proposed in Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection by Shilong L…
🧩 google/siglip2-giant-opt-patch16-384
通用·自然图像通用 ·7.53 GB ·↓ 1,883,186 ·♥ 55
SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved sema…
🔒 facebook/sam3
通用·分割/检测/深度 ·6.9 GB ·↓ 1,864,206 ·♥ 4917
SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text o…
🧩 google/siglip2-base-patch16-224
通用·自然图像通用 ·1.54 GB ·↓ 1,651,171 ·♥ 156
SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved sema…

如何使用