PulseAugur
LIVE 09:05:07
research · [2 sources] · · 日本語(JA) 【Granite Embedding Multilingual R2: Open Apache 2.0 多言語埋め込み (32K コンテキスト付き) — 100M 未満の検索品質が最高】 https:// huggingface.co/blog/ibm-granit e/granite-embedding-multil
16
research

Hugging Face releases Holotron-12B and Granite Embedding Multilingual R2

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 2 sources

Hugging Face has announced two new open-source models: Holotron-12B, designed for high-throughput computer use agents, and Granite Embedding Multilingual R2, which offers multilingual embeddings with a 32K context window. The Granite model aims for top-tier search quality with under 100 million parameters. Both releases are available under open-source licenses. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Expands open-source options for AI agents and multilingual embedding tasks.

RANK_REASON The cluster contains announcements of new open-source models released on Hugging Face.

Read on Mastodon — sigmoid.social →

COVERAGE [2]

  1. Mastodon — sigmoid.social TIER_1 日本語(JA) · [email protected] ·

    Holotron-12B - High-Throughput Computer Use Agent https:// huggingface.co/blog/Hcompany/h olotron-12b * AI-generated automatic post (headline + link) # AI # GenerativeAI # LLM # AIGenerated

    【Holotron-12B - 高スループットコンピュータ使用エージェント】 https:// huggingface.co/blog/Hcompany/h olotron-12b ※AI生成の自動投稿（見出し＋リンク） # AI # 生成AI # LLM # AIGenerated

    LINKS huggingface.co/…/holotron-12b
  2. Mastodon — sigmoid.social TIER_1 日本語(JA) · [email protected] ·

    Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings (with 32K Context) — Search Quality Under 100M is Top-Tier

    【Granite Embedding Multilingual R2: Open Apache 2.0 多言語埋め込み (32K コンテキスト付き) — 100M 未満の検索品質が最高】 https:// huggingface.co/blog/ibm-granit e/granite-embedding-multilingual-r2 ※AI生成の自動投稿（見出し＋リンク） # AI # 生成AI # LLM # AIGenerated

    LINKS huggingface.co/…/granite-embedding-multil…

RELATED ENTITIES

RELATED TOPICS