Kakao Brain 於 Hugging Face 釋出全新 ViT 與 ALIGN 開源模型
Original: New ViT and ALIGN Models From Kakao Brain
Kakao Brain, the AI research arm of South Korean tech giant Kakao, has officially released newly trained ViT (Vision Transformer) and ALIGN…
韓國科技巨頭 Kakao 旗下的 AI 研究部門 Kakao Brain，在 Hugging Face 上釋出了全新的 ViT 與 ALIGN 模型。這些模型基於其先前開源的 COYO-700M 超大規模圖文對數據集進行訓練。本次開源不僅補足了 ALIGN 模型缺乏開源權重的遺憾，也為多模態表徵、圖像檢索與零樣本分類等任務提供了強大的新選擇。
Kakao Brain, the AI research arm of South Korean tech giant Kakao, has officially released newly trained ViT (Vision Transformer) and ALIGN (A Large-scale Image and Noisy-text Embedding) model weights on the Hugging Face platform.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Hugging Face Blog →Summaries are AI-generated; the original article is authoritative.