Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models
Paper
• 2501.17088 • Published
• 2
Compressed Mamba Models via Mamba-Shedder (Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models)
Note Compressed Mamba-2.8B
Note Compressed Mamba2-2.7B