What kind of training data used in the RL process of R1 Zero?
#14 opened about 13 hours ago
by
RitchieLeung
DEEPSEEK NIUBI
#11 opened 1 day ago
by
jacknotexists
Add meta data
#9 opened 2 days ago
by
not-lain
Thank you deepseek
2
#8 opened 2 days ago
by
teknium
when release the technical report.
3
#6 opened 3 days ago
by
yzg37166
A milestone
1
#4 opened 3 days ago
by
jiangxg
Hail CCP!!! God bless Chyna!
7
#3 opened 3 days ago
by
mnemojeet
The ASI-Godsend will happen.
1
#2 opened 3 days ago
by
AntDX316
Waiting!
4
#1 opened 3 days ago
by
syslot