home
-
all
|
technology
-
piracy
-
linux
-
memes
-
asklemmy
-
selfhosted
-
world
-
technology
-
nostupidquestions
-
mildlyinfuriating
-
technology
-
youshouldknow
-
worldnews
-
programmerhumor
-
games
-
privacy
-
gaming
-
opensource
-
showerthoughts
-
lemmyworld
-
more »
log in
or
sign up
|
settings
machinelearning@lemmy.ml
comments
8
By using the same techniques Google used to solve Go (MTCS and backprop), Llama8B gets 96.7% on math benchmark GSM8K. That’s better than GPT-4, Claude and Gemini, with 200x fewer parameters!
(arxiv.org)
submitted
2 months ago
* (last edited
2 months ago
) by
yogthos@lemmy.ml
to
c/machinelearning@lemmy.ml
2 comments
fedilink
hide all child comments
top 2 comments
sorted by:
hot
top
controversial
new
old
[-]
shasta@lemm.ee
2 points
2 months ago
Fewer
permalink
fedilink
source
hide
show 2
child comments
[-]
yogthos@lemmy.ml
2 points
2 months ago
Fine
permalink
fedilink
source
this post was submitted on 16 Jun 2024
8
points
(78.6% liked)
Machine Learning
1717 readers
2 users here now
founded 4 years ago
MODERATORS
osipov@lemmy.ml