PulseAugur
EN
LIVE 10:49:03

Liquid AI releases compact multilingual search models for edge devices

Liquid AI has launched two new retrieval models, LFM2.5-Embedding-350M and LFM2.5-ColBERT-350M, each with 350 million parameters. These models are designed for efficient multilingual search across 11 languages and can operate on edge devices and laptops. They utilize a bidirectional architecture to provide rapid local search capabilities. AI

IMPACT Enables efficient multilingual search capabilities on edge devices and laptops.

RANK_REASON Frontier-lab model release with system card [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Liquid AI releases compact multilingual search models for edge devices

COVERAGE [2]

  1. Mastodon — mastodon.social TIER_1 Polski(PL) · aisight ·

    Liquid AI introduces LFM2.5-ColBERT and LFM2.5-Embedding models, which despite their compact size, outperform larger competitors in multilingual tests. Thanks to

    Liquid AI wprowadza modele LFM2.5-ColBERT i LFM2.5-Embedding, które mimo kompaktowych rozmiarów deklasują większą konkurencję w testach wielojęzycznych. Dzięki architekturze dwukierunkowej systemy te oferują błyskawiczne wyszukiwanie lokalne na laptopach i urządzeniach brzegowych…

  2. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Liquid AI has released two new retrieval models for multilingual search across 11 languages. The LFM2.5-Embedding-350M dense bi-encoder and LFM2.5-ColBERT-350M

    Liquid AI has released two new retrieval models for multilingual search across 11 languages. The LFM2.5-Embedding-350M dense bi-encoder and LFM2.5-ColBERT-350M late-interaction model both have 350M parameters and run on edge devices. Available on Hugging Face. https://www. markte…