qwertyu
gagfafsdgsdfgs
AI & ML interests
None yet
Recent Activity
New activity
23 days ago
amd/AMD-OLMo:DPO'ed model performs even worse on RLHF benchmarks???
Organizations
None yet
gagfafsdgsdfgs's activity
DPO'ed model performs even worse on RLHF benchmarks???
#1 opened 23 days ago
by
gagfafsdgsdfgs