OpenSearch's new retrievers are Apache 2.0 and drop straight into Sentence Transformers
tomaarsen · x · 2026-11-13
tomaarsen adds that OpenSearch's two new models — the asymmetric sparse model and the first dense embedding model — are English and Apache 2.0 licensed, with learned sparse vectors via SparseEncoder and dense vectors via SentenceTransformer, so both drop straight into the Sentence Transformers ecosystem. He praises the OpenSearch team and reiterates that sparse models are underrated.
Related event: OpenSearch Releases First Open-Source Embedding and Sparse Retrieval Models(3 posts)→
More from Models
- Edge0-145B-NVFP4 trends on Hugging Face: a 4-bit MoE built for edge inference — Edge0 · 2026-11-14
- Drex Max v1.1 claims #1 on Artificial Analysis Decision Index at $103/1M tasks — JaynitMakwana · 2026-11-14
- XERJ Reader-1 launches: neurosymbolic verifiable document parsing at $0.01 per 1M tokens — socialwithaayan · 2026-11-14
- Gemini completely failed to identify an AI-generated image in user test — Less-Ice2477 · 2026-11-14
- The Newest LLM Isn't Automatically the Best Business Choice — DavidLinthicum · 2026-11-14
- ChatGPT now shows disclaimers in replies and cites sources by name — lilyraynyc · 2026-11-14