|
|
|
|
|
|
by nickpsecurity
845 days ago
|
|
|
Some prior comments said those architectures lack the memory or something of a transformer. That there’s a weakness that’s keeping people using transformers. If true, I’d like to also see tests of various domains with equivalent transformer and Mamba designs to see if that difference impacted anything. From there, we’d have a better idea about whether Mamba-176B is worth the money. |
|
|