New releaseImproving Hugging Face Training Efficiency Through Packing with Flash Attention 2Hugging Face Blog · 1 min read
UpdateA failed experiment: Infini-Attention, and why we should keep trying?Hugging Face Blog · 1 min read
New releaseWelcome Falcon Mamba: The first strong attention-free 7B modelHugging Face Blog · 1 min read