New discussion

Increase drop out for gpt neo

1
#11 opened about 1 year ago by SUNM

Flash attention

#8 opened over 1 year ago by Xyzzyxsfr

Demo code for GPT-NEO 2.7B

#6 opened over 1 year ago by toncho11

utilizing tensor cores

#3 opened over 1 year ago by uberthoth

stop sequence

1
#2 opened over 1 year ago by LavGadewar