Transformers

• Hymba, a new breed of SSM-Attention Hybrids December 2, 2024
• Distilling State Space Models from Transformers October 28, 2024
• Mamba(2) and Transformer Hybrids: An Overview September 18, 2024
• BinT5 and HexT5 or T5 and Binary Reverse Engineering June 12, 2024
• CodeT5 and CodeT5+ June 1, 2024
• Longer Context for T5 April 29, 2024
• T5 the Old New Thing March 6, 2024