Why is <think></think> required in history messages?
#4 opened 1 day ago
by
giangndm
Terrible instruction following
4
#3 opened 1 day ago
by
denisalpino
4b model with an 84.2 MMLU-Redux score?
๐ค
1
#2 opened 1 day ago
by
phil111
when 32B?
๐
5
2
#1 opened 2 days ago
by
AaronFeng753