aiqbenchInformații despre AI & calcul cuantic

...

localeBeta.label localeBeta.notice localeBeta.readInEnglish

perspectiva aiqbenchProduse AI

Linkup Research has introduced SPARSEUP, an open-source sparse embedding model that achieves state-of-the-art retrieval performance under 150M parameters using a ModernBERT backbone. By employing logit shifting and per-token top-k expansion, the model effectively mitigates stopword noise while maintaining compatibility with inverted indexes for efficient querying. This release completes a comparative suite alongside recent dense models from LightOn, offering researchers a standardized benchmark for evaluating different retrieval architectures on public datasets.

Sursă care acoperăMarkTechPost

Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

Linkup Research Releases SPARSEUP: A 149M-Parameter Open-Source Sparse Embedding Model

MarkTechPost19 septembrie 20264 min de cititArticolul și perspectiva sunt în engleză.

Linkup Research has released SPARSEUP, an open-source sparse embedding model built on a 149M-parameter ModernBERT backbone. It scores 56.4 nDCG@10 on BEIR-13, which Linkup calls the best result it knows of for a public sparse encoder under 150M parameters. The model uses a logit shift, top-12 expansion per token and case folding to keep its vectors sparse. With the Seismic index, it reaches over 97% recall in about 380 microseconds per query, and it ships under Apache 2.0. The post Linkup Research Releases SPARSEUP: A 149M-Parameter Open-Source Sparse Embedding Model appeared first on MarkTechPost.

Linkup research team releases SPARSEUP, an open-source learned sparse embedding model. The model runs on a 149M-parameter ModernBERT backbone and ships under Apache 2.0. Linkup team reports 56.4 average nDCG@10 on BEIR-13. It calls this the strongest public vocabulary-based sparse encoder it knows of under 150M parameters. Is it deployable? Yes. The weights are on Hugging Face under Apache 2.0. The model loads through Transformers or…

Extras afișat conform termenilor RSS ai publicației · 66 cuvinte · textul integral și figurile sunt pe site-ul publicației

Citește pe MarkTechPost ↗Întreabă despre acest articol