Liquid AI has launched two new retrieval models, LFM2.5-Embedding-350M and LFM2.5-ColBERT-350M, designed for efficient multilingual search in 11 languages. These models, each with 350 million parameters, are capable of running on edge devices. They are now accessible on the Hugging Face platform. AI
IMPACT Enables faster, more efficient multilingual search capabilities on edge devices.
RANK_REASON Release of new models by a company, not a frontier lab. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Mastodon — mastodon.social →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
