歡迎 Falcon Mamba：首款強大的無注意力機制（Attention-Free）7B 語言模型
Original: Welcome Falcon Mamba: The first strong attention-free 7B model
The Technology Innovation Institute (TII) of Abu Dhabi has officially released Falcon Mamba 7B, a significant milestone in the evolution of…
阿布達比技術創新研究所（TII）推出 Falcon Mamba 7B，這是首個在效能上能與主流 Transformer 抗衡的無注意力機制（Attention-free）模型。基於 Mamba 狀態空間模型（SSM）架構，它在處理極長文本時具有記憶體佔用恆定與推論速度極快的優勢，並以 Apache 2.0 協議開源。
The Technology Innovation Institute (TII) of Abu Dhabi has officially released Falcon Mamba 7B, a significant milestone in the evolution of AI architectures. It is the first 7-billion-parameter-scale model to match the performance of traditional Transformer models (such as Llama 3 or Mistral) while being entirely attention-free.
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.