WeMM-Embedding

About

What WeMM-Embedding is

WeMM-Embedding-2B [](https://huggingface.co/collections/tencent/wemm-embedding) [](https://arxiv.org/abs/2608.24053) [](https://github.com/Tencent/WeMM-Embedding) WeMM-Embedding-2B is a universal multimodal embedding model built on Qwen3.5. It accepts text, images, videos, visual documents, and interleaved multimodal inputs, and returns a 2,048-dimensional L2-normalized embedding. Audio input is not supported. Derivation 本仓库为 tencent/WeMM-Embedding-2B 的 GGUF 格式量化版本。 - 两个量化文件的 GGUF 元数据已注入 qwen35.poolingtype=3（last-token pooling），Ollama 可直接识别为 embedding 模型使用。 - mmproj-WeMM-Embedding-2B-bf16.gguf 为独立导出的视觉塔（projector），用于多模态加载。 Installation Transformers Use any subset of the content items to encode text, image, or video independently. Sentence Transformers Each input is a string, a URL or path, a PIL.Image, or a dict combining image, video, and text keys. Put image or video before text so the prompt matches the ordering used above. Chat messages such as {"role": "user", "content": [{"type": "image", "image": ...}, {"type": "text", "text": ...}]} are also accepted, which is the way to interleave several images or videos in one input. Matryoshka Embeddings With Sentence Transformers, pass truncatedim and let it renormalize: Use a dimension listed in model.config.matryoshkadimensions. On MMEB-v2, 256-dimensional embeddings retain 98.7% of the full-dimensional image and video performance. Serving vLLM 0.27.0: SGLang 0.5.9: Evaluation MMEB-v2 Results on 78 datasets from Table 1 of the technical report. Image and video tasks use Hit@1, while visual-document tasks use NDCG@5. Higher is better. † Closed-source leaderboard submission without publicly released model weights or a public inference endpoint. MMEB-v3 Results on all 190 tasks from Table 2 of the technical report. V3-All includes the 78 MMEB-v2 tasks, 53 text tasks, 47 agent tasks, 11 audio tasks, and MCMR. Unsupported tasks are assigned a score of zero. Text results use NDCG@5; agent, MCMR, and audio results use Hit@1. Citation If you find this repository useful, please consider giving a star ⭐ and citation License WeMM-Embedding-2B, including the code, model parameters, and weights made publicly available by Tence

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How embedding models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys dreamblooms-wemm-embedding for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (dreamblooms-wemm-embedding below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"dreamblooms-wemm-embedding","input":"text to embed"}'

Details

Languages, data & research

Papers

Licence

Commercial licence needed

Sources

Weights & code

Explore

More embedding models