Dr3dre/ppo-noise-pythia-1b-deduped-lr2e-06-effbs64-ep1-0-noise-poison-70 Text Generation • 1B • Updated Feb 8 • 5
Dr3dre/ppo-noise-pythia-1b-deduped-lr2e-06-effbs64-ep1-0-noise-poison-50 Text Generation • 1B • Updated Feb 8 • 5
Dr3dre/ppo-noise-pythia-1b-deduped-lr2e-06-effbs64-ep1-0-noise-poison-20 Text Generation • 1B • Updated Feb 8 • 6
Dr3dre/ppo-noise-pythia-1b-deduped-lr2e-06-effbs64-ep1-0-noise-poison-10 Text Generation • 1B • Updated Feb 8 • 7
Dr3dre/ppo-flip-labels-pythia-1b-deduped-lr1e-06-effbs64-ep1-0-eos-penalty-1-0-warmup-0-15 Text Generation • 1B • Updated Feb 2 • 6
Dr3dre/rm-oai-paraphrase-pythia-1b-deduped-lr6-35e-05-effbs128-ep1-0-lr1-5e-05-effbs64-ep1-0 Text Classification • 0.9B • Updated Feb 2 • 4
Dr3dre/rm-oai-flip-labels-pythia-1b-deduped-lr6-35e-05-effbs128-ep1-0-lr1-5e-05-effbs64-ep1-0-flip Text Classification • 0.9B • Updated Feb 2 • 10
Dr3dre/rm-oai-pythia-1b-deduped-lr6-35e-05-effbs128-ep1-0-lr1-5e-05-effbs64-ep1-0 Text Classification • 0.9B • Updated Feb 2 • 22
Dr3dre/rm-length-bonus-pythia-1b-deduped-lr6-35e-05-effbs128-ep1-0-lr1-5e-05-effbs64-ep1-0-shortbonus Text Classification • 0.9B • Updated Feb 2 • 3
Dr3dre/rm-length-bonus-pythia-1b-deduped-lr6-35e-05-effbs128-ep1-0-lr1-5e-05-effbs64-ep1-0-longbonus Text Classification • 0.9B • Updated Feb 2 • 3
Dr3dre/rm-pythia-1b-deduped-lr3e-06-effbs256-ep1-0-lr3e-06-effbs64-ep1-0 Text Classification • 0.9B • Updated Feb 2 • 4
Dr3dre/ppo-short-summary-bonus-pythia-1b-deduped-lr2e-06-effbs64-ep1-0-short-summary-bonus Text Generation • 1B • Updated Feb 2 • 6
Dr3dre/ppo-paraphrase-pythia-1b-deduped-lr2e-06-effbs64-ep1-0 Text Generation • 1B • Updated Feb 2 • 5
Dr3dre/ppo-long-summary-bonus-pythia-1b-deduped-lr2e-06-effbs64-ep1-0-long-summary-bonus Text Generation • 1B • Updated Feb 2 • 4
Dr3dre/ppo-pythia-1b-deduped-lr2e-06-effbs64-ep1-0-missing-eos-penalty-1-0 Text Generation • 1B • Updated Feb 2 • 3
Dr3dre/rm-test-pythia-1b-deduped-lr3e-06-effbs256-ep1-0-lr3e-06-effbs128-ep1-0 Text Classification • 0.9B • Updated Feb 2 • 4
Dr3dre/RM-pythia-1b-deduped_lr3e-06_effbs256_ep1.0_lr3e-06_effbs128_ep1.0 Text Classification • 0.9B • Updated Jan 21 • 3