Tencent's retrieval models dominate Hugging Face trends with 4 entries
tomaarsen · x · 2026-09-14
Tomaarsen, author of Sentence Transformers, notes that Tencent's team has been exceptionally productive in search/retrieval models: 4 of their recent models are simultaneously trending among all Sentence Transformers models on Hugging Face.
EVIE and WeMM are both strong multimodal (text + image) embedding models, covering multi-vector (late interaction) and dense retrieval respectively.
Related event: Tencent Releases Multiple Retrieval Models, Four Hit HF Trending(2 posts)→
More from Models
- Fudan NLP paper explains why max reasoning settings can backfire on SWE benchmarks — karminski3 · 2026-09-14
- Muse Spark 1.3 impresses at coding, but where's the promised open source release? — formatme · 2026-09-14
- Tencent releases EVIE visual document retrieval models as Apache 2.0 preview — tomaarsen · 2026-09-14
- GPT-6 Astra reportedly solves Portal and Baba Is You puzzles, unverified — pmigdal · 2026-09-14
- Skeptic questions GPT-6 Astra's near-perfect robotics score: model or test conditions? — GeorgiaChal · 2026-09-14
- Rumor: OpenAI to unveil GPT-6 Spark at Dev Day — imjustnewatai · 2026-09-14