/top/
/new/
/best/
/ask/
/show/
/job/
^
slacker news
login
about
←back to thread
Zamba2-7B
(www.zyphra.com)
282 points
dataminer
| 1 comments |
14 Oct 24 22:45 UTC
|
HN request time: 0.205s
|
source
Show context
PoignardAzur
◴[
15 Oct 24 09:14 UTC
]
No.
41846612
[source]
▶
>>41842975 (OP)
#
For the amount of theoretical work behind those Mamba2 blocks (I can barely understand their paper on the subject), those are some extremely modest performance gains.
Attention remains king.
replies(2):
>>41848095
#
>>41849186
#
1.
erichocean
◴[
15 Oct 24 12:57 UTC
]
No.
41848095
[source]
▶
>>41846612
#
Mamba is also much more efficient, watt-wise, to run.
ID:
GO
↑