Tencent/WeMM-Embedding
- Total stars
- 1,713
- Today
- +0
More actions
WeMM-Embedding is a family of universal multimodal embedding models by the WeChat Vision Team at Tencent, supporting multimodal understanding and retrieval.
Save to My finds to follow releases and star growth. Saved in this browser.
About the project
A family of universal multimodal embedding models from Tencent's WeChat Vision team (2B, 4B, 9B) producing unified vectors for text, images, videos, visual documents, and interleaved multimodal inputs. Supports Matryoshka dimensions and serving via vLLM/SGLang.
Useful for
- Build multimodal retrieval over a mixed corpus of images, videos, and documents with one index
- Truncate embeddings to 256 dimensions via Matryoshka to save memory with minimal quality loss
- Serve embeddings for text and video online using vLLM or SGLang
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate. Read the original README →
Star growth looks organic. Data as of October 4, 2026, 00:26 UTC.
The star-growth assessment does not verify whether the project is safe to run.
Stars per day
Bars show stars per UTC day; the line is a moving average of available history. Gaps mean missing data, not zero growth. Today's bar is incomplete. Red marks spike days.
Why it’s trending
- 0 stars so far today, about 6 expected by the end of the day.
- The repository is 40 days old and already has 1,713 stars.
Measured growth: the last 7 completed days
The full 7-day window is unavailable; no weekly total or comparison is calculated.
Daily measurements · UTC
- October 22, 2026
- —
- October 23, 2026
- —
- October 24, 2026
- —
- October 25, 2026
- —
- October 26, 2026
- —
- October 27, 2026
- —
- October 28, 2026
- —
Largest measured day in the last 30 days: 11 · September 29, 2026. Days with data: 5.
Completed days come from GitHub star history; today and forecasts are excluded from this comparison. History checked: October 4, 2026, 00:26 UTC. Sources and measurement limits →
Three GitHub discoveries in each edition
What they do, why they are gaining interest, and what to check before using them.
Editions at 10:00, 16:00, 22:00 MSK.
Numbers
- Total stars
- 1,713
- Today
- +0 stars on 2026-10-04 (UTC), ≈ 6 by evening
- Forks
- 120
- Issues and pull requests
- 13
- Watchers
- 11
- Language
- Python
- Created
- August 25, 2026
- Last push
- September 20, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 23, 2026Top new repositories this month: #42
- September 22, 2026Top new repositories this month: #42
- September 21, 2026Top new repositories this month: #42
- September 20, 2026Top new repositories this month: #46
- September 19, 2026Top new repositories this month: #45
- September 18, 2026Top new repositories this month: #42
- September 17, 2026Top new repositories this month: #40
- September 16, 2026Top new repositories this month: #40
- September 15, 2026Top new repositories this month: #40
- September 14, 2026Top new repositories this month: #37
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/Tencent/WeMM-Embedding)