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 →