Tencent/WeMM-Embedding
WeMM-Embedding is a family of universal multimodal embedding models by the WeChat Vision Team at Tencent, supporting multimodal understanding and retrieval.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
WeMM-Embedding: WeChat Multi-Modal Embedding English | 中文 WeMM-Embedding is a family of universal multimodal embedding models developed by the WeChat Vision team. It provides unified representations for text, images, videos, visual documents, and interleaved multimodal inputs, achieving state-of-the-art performance across multiple benchmarks covering diverse tasks and domains. All models support text, images, videos, visual documents, and interleaved multimodal inputs. Embeddings are obtained from the last-layer hidden state at the dedicated token position, followed by L2 normalization. Audio input is not currently supported. The snippet below is fully standalone: it does not use any code or files from this repository, and the image is loaded from a URL. Just install the dependencies, save the code as demo.py, and run python demo.py: The first text should have a higher similarity to the image than the second one. We recommend using transformers==5.2.0 for inference and reproducibility, as newer versions may differ in preprocessing…
Read the full README ↗ · Preview checked 2026-10-30T02:30:24.138Z
Inside the original README — Document outline
- Model Zoo
- Installation
- Quick Start
- Transformers
- Sentence Transformers
- Serving
- Matryoshka Embeddings
- Evaluation
- MMEB-v2
- MMEB-v3
- Citation
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
WeMM-Embedding is a family of universal multimodal embedding models by the WeChat Vision Team at Tencent, supporting multimodal understanding and retrieval.
Repository facts
- Owner
- Tencent
- Primary language
- Python
- Stars
- 1,665
- Forks
- 117
- Open issues + pull requests
- 2
- License
- Other
- Archived
- No
- Default branch
- main
- Created
- 2026-08-25T02:46:10.000Z
- Last push
- 2026-09-20T14:09:11.000Z
Topics and intended use
Owner-supplied topics: embedding-models, multimodal, multimodal-llm
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-09-24T12:04:33.563Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer