/top/
/new/
/best/
/ask/
/show/
/job/
^
slacker news
login
about
←back to thread
Mercury: Ultra-fast language models based on diffusion
(arxiv.org)
566 points
PaulHoule
| 1 comments |
07 Jul 25 12:31 UTC
|
HN request time: 0.224s
|
source
1.
numpad0
◴[
08 Jul 25 00:47 UTC
]
No.
44495948
[source]
▶
>>44489690 (OP)
#
Is parameter count published? I'm by no means expert, but failure modes remind me of Chinese 1B class models.
ID:
GO
↑