DevTechNodeabout 3 hours ago
WeChat open-sources WeMM-Embedding multimodal models
1 min read
Tencent's WeChat Vision team open-sourced WeMM-Embedding, a family of multimodal embedding models for text, images, and videos. The release includes 2B, 4B, and 9B versions, already deployed in WeChat Channels, Official Accounts, Moments, and e-commerce. The 9B model ranks first on MMEB-v2 and MMEB-v3 benchmarks.
Level
Hype check
Tap to vote and see what everyone thinks.
