petrescatraian@libranet.de to Technology@beehaw.org · 3 months agoDeepseek when asked about sensitive topicsi.postimg.ccimagemessage-square86fedilinkarrow-up1312file-text
arrow-up1312imageDeepseek when asked about sensitive topicsi.postimg.ccpetrescatraian@libranet.de to Technology@beehaw.org · 3 months agomessage-square86fedilinkfile-text
minus-squareAatube@kbin.melroy.orglinkfedilinkarrow-up1·3 months agoDid you use the -Zero model, which doesn’t have the “cold-start data before RL” which prevents it from language mixing?
Did you use the -Zero model, which doesn’t have the “cold-start data before RL” which prevents it from language mixing?