Tencent Open-Sourced the Model Behind WeChat Search
Summary
WeMM-Embedding is a family of universal multimodal embedding models from the WeChat Vision team, open-sourced under Apache 2.0 in sizes 2B, 4B, and 9B. The 9B now tops the MMEB-v2 leaderboard (80.6 average over 78 datasets) ahead of every open and closed model listed, and the 2B beats the previous best small models. WeChat already runs it in production across search, recommendations, and shopping, where it won 14 live A/B tests before the paper published. The trick worth stealing: Matryoshka truncation chops each embedding to an eighth of its size while keeping almost 99% of the accuracy, an eighth of the storage on a vector store bill. Text, images, video, and documents; no audio yet. Models and paper: github.com/Tencent/WeMM-Embedding
About this video
WeMM-Embedding is a family of universal multimodal embedding models from the WeChat Vision team, open-sourced under Apache 2.0 in sizes 2B, 4B, and 9B. The 9B now tops the MMEB-v2 leaderboard (80.6 average over 78 datasets) ahead of every open and closed model listed, and the 2B beats the previous best small models. WeChat already runs it in production across search, recommendations, and shopping, where it won 14 live A/B tests before the paper published. The trick worth stealing: Matryoshka truncation chops each embedding to an eighth of its size while keeping almost 99% of the accuracy, an eighth of the storage on a vector store bill. Text, images, video, and documents; no audio yet. Models and paper: github.com/Tencent/WeMM-Embedding