English(EN) 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 发布面向边缘设备的多语言检索模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-19 11:12

Liquid AI 推出了两个新的检索模型 LFM2.5-Embedding-350M 和 LFM2.5-ColBERT-350M，专为 11 种语言的高效多语言搜索而设计。这两个模型各有 3.5 亿个参数，能够运行在边缘设备上。它们现已在 Hugging Face 平台上可用。 AI

影响在边缘设备上实现更快、更高效的多语言搜索功能。

排序理由由一家公司发布新模型，而非前沿实验室。[lever_c_降级自研究：ic=1 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

报道来源 [1]

Mastodon — mastodon.social TIER_1 English(EN) · [email protected] · 2026-06-19 11:12

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…

报道来源 [1]

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

相关实体

相关话题