kaideng

dk666's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

commented a paper 1 day ago

SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration

Paper • 2411.10958 • Published 6 days ago • 41 •

6

liked a model 9 months ago

HuggingFaceH4/zephyr-7b-beta

Text Generation • Updated Oct 16 • 488k • • 1.61k