selfcorrexp2/llama3_sft_balanced_rr60k_train_on_corr_ep3_full_testtmp07_vllmexp Viewer • Updated about 9 hours ago • 15k
selfcorrexp2/llama3_sft_balanced_rr60k_train_on_corr_ep3_full_testtmp10_vllmexp Viewer • Updated about 9 hours ago • 15k
selfcorrexp2/Hanning_Llama3-sft-less-corr-rr60k-3eptmp07_vllmexp Viewer • Updated about 10 hours ago • 5k